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

    Neuronpedia

    INDEX
    Explanations

    words/phrases related to actions or activities involving learning, receiving, sending, challenging, providing, experimenting, and so forth

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "we" and associated pronouns to indicate collective action or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.67
     interfering
    -0.60
     Kang
    -0.60
     Outside
    -0.58
    uggle
    -0.57
     Peak
    -0.57
    ultan
    -0.57
     Kill
    -0.57
     Killing
    -0.56
    acher
    -0.56
    POSITIVE LOGITS
    'll
    0.88
     hereby
    0.82
    bra
    0.74
    'd
    0.74
     reasoned
    0.71
    've
    0.68
    ttes
    0.67
     sugg
    0.66
     must
    0.65
    CLA
    0.64
    Act Density 0.388%

    No Known Activations