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

    Neuronpedia

    INDEX
    Explanations

    terms related to agreements, contracts, and organizational structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     auffi
    -0.93
     purpoſe
    -0.92
     myſelf
    -0.86
     itſelf
    -0.84
    Portail
    -0.83
     uſed
    -0.83
     незавершена
    -0.81
     pleaſure
    -0.80
     himſelf
    -0.79
     Efq
    -0.77
    POSITIVE LOGITS
    calciatore
    0.49
    œ
    0.46
    pera
    0.42
     man
    0.42
     Y
    0.41
    ########.
    0.41
    underline
    0.40
    <eos>
    0.40
     
    0.39
     ,
    0.39
    Act Density 2.879%

    No Known Activations