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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mar
    -0.64
     A
    -0.63
    <em>
    -0.61
    Pp
    -0.61
     Lovel
    -0.61
     tø
    -0.60
     a
    -0.60
    prevState
    -0.57
    و
    -0.57
     The
    -0.57
    POSITIVE LOGITS
    1.07
     myſelf
    0.97
     Majefty
    0.96
     ―――――
    0.95
    )");
    0.95
    ."));
    0.94
     ſche
    0.94
     purpoſe
    0.94
    Datuak
    0.93
     Diſ
    0.92
    Act Density 0.658%

    No Known Activations