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

    Neuronpedia

    INDEX
    Explanations

    terms related to approvals and consent processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.60
    -
    -0.53
    ya
    -0.51
     h
    -0.51
     c
    -0.50
    7
    -0.50
    5
    -0.49
    寡
    -0.49
     g
    -0.48
    en
    -0.48
    POSITIVE LOGITS
     @"/
    1.08
     auffi
    0.95
     ainfi
    0.92
     Efq
    0.90
     provisoire
    0.87
    SEGUIR
    0.87
     citoy
    0.87
     myſelf
    0.86
    CloseOperation
    0.85
    ^(@)
    0.85
    Act Density 0.192%

    No Known Activations