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

    Neuronpedia

    INDEX
    Explanations

    terms related to reporting and feedback within an evaluative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pto
    -0.15
    vr
    -0.15
    ank
    -0.14
    há
    -0.14
    imal
    -0.14
    -0.14
    hec
    -0.14
    738
    -0.14
    erner
    -0.13
    uÃŃ
    -0.13
    POSITIVE LOGITS
    edly
    0.36
    orial
    0.32
     cáo
    0.21
    eza
    0.19
    ees
    0.17
    /report
    0.17
    age
    0.17
    /xhtml
    0.17
    eurs
    0.17
    สà¸Ķ
    0.16
    Act Density 0.055%

    No Known Activations