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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or initiative

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to going out and actions taken in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufficient
    -0.64
     Sovere
    -0.64
    cious
    -0.63
     Presence
    -0.57
    ulty
    -0.56
    Sal
    -0.55
    POS
    -0.55
    cup
    -0.55
    lement
    -0.54
     KING
    -0.54
    POSITIVE LOGITS
    mans
    0.75
     spree
    0.73
     lengths
    0.71
     rant
    0.70
     shopping
    0.69
    onyms
    0.69
     bashing
    0.67
     looting
    0.66
    neys
    0.64
    umblr
    0.64
    Act Density 0.276%

    No Known Activations