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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly related to performance statistics, measurements, or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beck
    -0.67
    agna
    -0.64
    yll
    -0.62
     recre
    -0.62
    arton
    -0.60
    rera
    -0.58
    zos
    -0.58
    croft
    -0.57
    akeru
    -0.56
    deen
    -0.56
    POSITIVE LOGITS
    /+
    1.57
    /-
    1.31
    dB
    1.07
     sqor
    1.05
    ï¸ı
    0.93
     dB
    0.83
    ½
    0.77
    °
    0.75
    ,-
    0.74
    MW
    0.73
    Act Density 0.017%

    No Known Activations