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

    Neuronpedia

    INDEX
    Explanations

    references to specific percentages and numerical thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olley
    -0.18
    posit
    -0.17
    ament
    -0.17
    ting
    -0.15
    relude
    -0.15
    meno
    -0.15
    ive
    -0.14
    igue
    -0.14
     Uhr
    -0.14
    urity
    -0.14
    POSITIVE LOGITS
    Ø©
    0.20
    eros
    0.16
    ecz
    0.16
     lại
    0.15
    न
    0.15
    Ø¡
    0.15
    zeitig
    0.15
    alker
    0.15
    aliyet
    0.14
    vron
    0.14
    Act Density 0.134%

    No Known Activations