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

    Neuronpedia

    INDEX
    Explanations

    references to collective beliefs and moral responsibility among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.55
     pleaſure
    -0.54
     उसने
    -0.53
     himſelf
    -0.52
     väli
    -0.52
    ValuePair
    -0.52
     purpoſe
    -0.52
     opér
    -0.51
     Vicksburg
    -0.49
     ساتھ
    -0.49
    POSITIVE LOGITS
    LookAnd
    0.82
    ftagPool
    0.70
    Humans
    0.70
     humans
    0.69
    دانشنامهٔ
    0.67
     your
    0.65
     you
    0.65
     human
    0.63
     tayo
    0.59
     Humans
    0.59
    Act Density 0.145%

    No Known Activations