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

    Neuronpedia

    INDEX
    Explanations

    sequences of alphanumeric characters and code-like syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffion
    -0.81
    ſtanding
    -0.77
    ſſer
    -0.73
    eſ
    -0.70
    ^(@)
    -0.68
    NUMX
    -0.67
    ARROLL
    -0.67
     autorytatywna
    -0.67
    leſs
    -0.67
    IsContent
    -0.66
    POSITIVE LOGITS
    //
    0.99
    +
    0.99
    q
    0.94
    v
    0.91
    z
    0.88
    7
    0.87
    4
    0.87
    S
    0.85
    ///
    0.85
    6
    0.84
    Act Density 0.049%

    No Known Activations