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

    Neuronpedia

    INDEX
    Explanations

    terms related to "ideal" or "idealized" concepts in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     [
    -0.70
    witz
    -0.67
     `
    -0.66
    fö
    -0.65
     –
    -0.63
     Montal
    -0.63
     McKenzie
    -0.63
    ….
    -0.62
    ムー
    -0.61
    ppert
    -0.61
    POSITIVE LOGITS
     Efq
    1.16
     myſelf
    1.07
     itſelf
    1.02
     contextLoads
    1.01
     himſelf
    0.98
     idéale
    0.96
     Jefus
    0.96
    '},
    0.95
     ainfi
    0.94
     neceff
    0.93
    Act Density 0.006%

    No Known Activations