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

    Neuronpedia

    INDEX
    Explanations

    discussions about change and personal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abra
    -0.18
     Qed
    -0.16
    aison
    -0.16
     Nur
    -0.15
    ystick
    -0.15
    _FA
    -0.14
    orz
    -0.14
    unca
    -0.14
     Tent
    -0.14
    igham
    -0.14
    POSITIVE LOGITS
    pery
    0.16
    bol
    0.15
    orer
    0.14
    ky
    0.14
    kr
    0.14
    plies
    0.14
    incy
    0.14
    _puts
    0.13
    ks
    0.13
    077
    0.13
    Act Density 0.187%

    No Known Activations