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

    Neuronpedia

    INDEX
    Explanations

    terms related to compactness

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    RICAL
    -0.86
     Réponses
    -0.86
     recip
    -0.69
    LVL
    -0.68
     Granger
    -0.68
     Bot
    -0.68
    orghini
    -0.67
    vVar
    -0.67
     lask
    -0.66
    (!__
    -0.66
    POSITIVE LOGITS
     compactness
    1.30
     Compact
    1.23
     compact
    1.17
    Compact
    1.16
    compact
    1.15
     compacto
    1.14
     compac
    0.93
     compacta
    0.91
     kompakt
    0.87
     kompak
    0.83
    Act Density 0.005%

    No Known Activations