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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forms and consultations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pron
    -0.17
    thouse
    -0.16
    reon
    -0.14
    amburger
    -0.14
    gow
    -0.14
    bih
    -0.14
    269
    -0.14
    anken
    -0.14
    onth
    -0.14
     extinction
    -0.14
    POSITIVE LOGITS
    agar
    0.16
     Odds
    0.15
    ă
    0.14
    aç
    0.14
    Hack
    0.14
    erala
    0.14
    asaki
    0.14
     Herman
    0.14
    yg
    0.14
     lorem
    0.14
    Act Density 0.062%

    No Known Activations