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

    Neuronpedia

    INDEX
    Explanations

    key words related to potential action or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ('
    -0.15
    igh
    -0.15
     instinct
    -0.14
     (
    -0.14
    pu
    -0.14
     damned
    -0.14
    ication
    -0.13
    ÌĢ
    -0.13
     (@
    -0.13
     ‘
    -0.13
    POSITIVE LOGITS
    bic
    0.15
    chal
    0.15
    aroo
    0.15
    <Test
    0.14
     hud
    0.14
     ä¿¡
    0.14
    _rng
    0.14
    grily
    0.13
    ourg
    0.13
    ondere
    0.13
    Act Density 0.000%

    No Known Activations