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

    Neuronpedia

    INDEX
    Explanations

    numerical statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    999
    -0.19
    501
    -0.19
    998
    -0.18
    401
    -0.16
    dux
    -0.16
    499
    -0.15
    dyby
    -0.15
     addCriterion
    -0.15
    249
    -0.14
    ÏĮγ
    -0.14
    POSITIVE LOGITS
    667
    0.17
    uckets
    0.15
    rif
    0.15
    eral
    0.14
    chin
    0.13
    Si
    0.13
    slaught
    0.13
     butt
    0.13
     TBD
    0.13
     Andrews
    0.13
    Act Density 0.046%

    No Known Activations