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

    Neuronpedia

    INDEX
    Explanations

    phrases related to one's role or position in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" and related contextual phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.85
    antine
    -0.75
    ratulations
    -0.74
    !--
    -0.71
    baum
    -0.69
    igmatic
    -0.68
     yourselves
    -0.66
    atform
    -0.65
    rox
    -0.65
    oing
    -0.63
    POSITIVE LOGITS
    stood
    0.65
    thood
    0.64
     Camel
    0.64
     Wonderland
    0.63
    tnc
    0.62
     diplomacy
    0.60
     Awakening
    0.58
     JS
    0.58
     mates
    0.57
     glory
    0.57
    Act Density 0.449%

    No Known Activations