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

    Neuronpedia

    INDEX
    Explanations

    patterns related to probability or frequency assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewater
    -0.17
    awy
    -0.16
     Kam
    -0.16
    egot
    -0.15
    reich
    -0.15
    ball
    -0.15
    hill
    -0.15
     S
    -0.14
    à¹Īาย
    -0.14
    reff
    -0.14
    POSITIVE LOGITS
    aze
    0.17
    DEC
    0.16
    izen
    0.15
    ix
    0.15
     Ru
    0.15
    ICS
    0.15
    _ru
    0.15
    _js
    0.14
    FI
    0.14
     Cro
    0.14
    Act Density 0.035%

    No Known Activations