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

    Neuronpedia

    INDEX
    Explanations

    terms related to supervision and supervisory roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .synthetic
    -0.15
    tres
    -0.15
    adelphia
    -0.15
    eresa
    -0.15
    .GetEnumerator
    -0.15
    ÑĥлÑĮ
    -0.15
    axies
    -0.14
    kola
    -0.14
    eras
    -0.14
    allon
    -0.14
    POSITIVE LOGITS
    267
    0.17
    ior
    0.17
    ors
    0.16
     heck
    0.16
    intendent
    0.15
    argas
    0.15
    888
    0.15
    etta
    0.15
    ial
    0.15
    375
    0.15
    Act Density 0.021%

    No Known Activations