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

    Neuronpedia

    INDEX
    Explanations

    instances where future plans or intentions are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    statements about intentions or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    int
    -0.73
    ashing
    -0.73
    inton
    -0.67
    cius
    -0.66
    acks
    -0.65
    weed
    -0.64
    hill
    -0.62
    picking
    -0.62
    wood
    -0.60
    anca
    -0.59
    POSITIVE LOGITS
     Parenthood
    0.87
    §
    0.80
    Īè
    0.73
    ±
    0.72
    0.69
    ŀ
    0.68
     accordingly
    0.67
    ħ
    0.66
    atorium
    0.66
    ģ
    0.66
    Act Density 0.057%

    No Known Activations