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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating areas and modes of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    delt
    -0.56
    i
    -0.54
     partea
    -0.52
    u
    -0.52
    utenants
    -0.51
     hap
    -0.50
     carav
    -0.50
     عج
    -0.50
     Konstruktion
    -0.49
     pembun
    -0.48
    POSITIVE LOGITS
    UIControlState
    1.01
    ]='\
    0.99
     }}$}
    0.99
    `,
    0.94
    [::-
    0.92
    }}]{
    0.91
    .}(
    0.91
    "])
    0.90
    "):
    0.89
    ".
    0.87
    Act Density 0.459%

    No Known Activations