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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making or evaluation criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awah
    -0.15
    721
    -0.15
    ëĵĿ
    -0.15
    tega
    -0.14
     *----------------------------------------------------------------
    -0.14
     Isl
    -0.13
    ạt
    -0.13
    ohl
    -0.13
    730
    -0.13
    220
    -0.13
    POSITIVE LOGITS
    itus
    0.15
    chte
    0.15
    antu
    0.15
    NONE
    0.15
    .Apis
    0.14
    ailles
    0.14
    levator
    0.14
    -none
    0.14
     none
    0.13
    senal
    0.13
    Act Density 0.000%

    No Known Activations