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

    Neuronpedia

    INDEX
    Explanations

    specific actions or states related to documentation or process indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SuppressMessage
    -0.64
    ,
    -0.48
     essentially
    -0.48
    서
    -0.47
     zwar
    -0.46
    муж
    -0.46
     protoimpl
    -0.45
    とにかく
    -0.45
     chi̍t
    -0.45
    each
    -0.44
    POSITIVE LOGITS
     Jefus
    0.83
     Majefty
    0.81
     Efq
    0.81
     pleaſure
    0.80
     myſelf
    0.78
     Monfieur
    0.78
     auffi
    0.77
     CreateTagHelper
    0.76
     purpoſe
    0.76
     himſelf
    0.75
    Act Density 0.810%

    No Known Activations