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

    Neuronpedia

    INDEX
    Explanations

    terms related to objectives or intentions behind actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mixing
    -0.48
     Lending
    -0.48
    ADT
    -0.47
     shooter
    -0.45
    cooling
    -0.44
     Signing
    -0.43
     mixer
    -0.43
    chance
    -0.43
    mixing
    -0.43
    discover
    -0.43
    POSITIVE LOGITS
    出版年
    0.60
     purpose
    0.60
     pharma
    0.57
     iter
    0.53
     autoridade
    0.49
     Pharma
    0.49
     autorité
    0.48
    ité
    0.48
     ailleurs
    0.47
    AndEndTag
    0.46
    Act Density 0.179%

    No Known Activations