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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications and authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olar
    -0.17
    олаг
    -0.16
    arty
    -0.16
    asta
    -0.16
    asso
    -0.16
    ure
    -0.16
    unch
    -0.15
    urge
    -0.15
    SizePolicy
    -0.15
    arth
    -0.15
    POSITIVE LOGITS
    reece
    0.18
    fe
    0.18
    onz
    0.17
    TOTYPE
    0.17
    licht
    0.16
    dyn
    0.16
    ichier
    0.16
     dyn
    0.16
    imen
    0.16
    fen
    0.16
    Act Density 0.045%

    No Known Activations