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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating actions or states of being in the context of different scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ally
    -0.71
    ically
    -0.71
    ablemente
    -0.68
     altrimenti
    -0.66
     siitä
    -0.58
    それで
    -0.57
    냅
    -0.56
    ably
    -0.55
    たびに
    -0.54
     있습니다
    -0.54
    POSITIVE LOGITS
    UVWXYZ
    0.89
     незавершена
    0.83
    {{$
    0.80
    irical
    0.77
     Haring
    0.76
    する
    0.75
    >');
    0.75
    ുന്ന
    0.74
    swire
    0.73
     /\.(
    0.72
    Act Density 0.039%

    No Known Activations