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

    Neuronpedia

    INDEX
    Explanations

    cryptic codes or labels associated with various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istical
    -0.73
     abstraction
    -0.68
    ial
    -0.64
    ened
    -0.64
    rade
    -0.64
     totality
    -0.63
     inev
    -0.60
     hiber
    -0.59
     movement
    -0.59
     econom
    -0.59
    POSITIVE LOGITS
    ensis
    0.80
    gmail
    0.78
    kens
    0.73
    alias
    0.73
    Downloadha
    0.70
     Malays
    0.68
     teasp
    0.68
     tradem
    0.67
    tein
    0.65
    byss
    0.65
    Act Density 0.752%

    No Known Activations