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

    Neuronpedia

    INDEX
    Explanations

    actions involving going to different places and performing specific tasks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iment
    -0.75
    人
    -0.64
    fur
    -0.63
    $$
    -0.61
    piration
    -0.61
    arter
    -0.61
    ander
    -0.60
    notations
    -0.58
     centr
    -0.58
    BIP
    -0.58
    POSITIVE LOGITS
     thence
    0.92
     whence
    0.76
     proceeded
    0.74
     befriend
    0.72
    romeda
    0.70
     ask
    0.69
     thus
    0.68
     partake
    0.68
     inund
    0.68
     then
    0.68
    Act Density 0.195%

    No Known Activations