Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to discussion and analysis of various subjects, highlighting popular culture and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Single words that provide essential context within sentences, often representing pronouns, location descriptors, attributions, or connecting terms that establish relationships between concepts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Negative Logits
     anfangen
    -0.37
     eigener
    -0.37
     ljudi
    -0.37
     yaptığı
    -0.36
     kepercayaan
    -0.36
     especializado
    -0.36
     especializada
    -0.36
     Publikum
    -0.36
     Mortimer
    -0.35
     zajíma
    -0.35
    POSITIVE LOGITS
    LookAnd
    0.69
    expandindo
    0.66
    OCCURRED
    0.66
     незавершена
    0.60
    featureID
    0.59
    IVEREF
    0.58
    parsedMessage
    0.58
     Infórmanos
    0.57
    ########.
    0.57
    новништво
    0.56
    Act Density 0.118%

    No Known Activations