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

    Neuronpedia

    INDEX
    Explanations

    questions that inquire about actions or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.19
    arella
    -0.17
    stanov
    -0.17
    ibold
    -0.17
    aginator
    -0.17
    borg
    -0.16
    neau
    -0.15
    miyor
    -0.14
    polator
    -0.14
    nero
    -0.14
    POSITIVE LOGITS
    ower
    0.15
    eldorf
    0.14
    /do
    0.14
    λÏĮ
    0.14
    /cat
    0.14
    ê»ĺ
    0.14
    els
    0.14
    eno
    0.13
    lectric
    0.13
     satisfaction
    0.13
    Act Density 0.049%

    No Known Activations