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

    Neuronpedia

    INDEX
    Explanations

    references to categories or classifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ething
    -0.17
    ALES
    -0.15
    _pk
    -0.15
    uard
    -0.15
    ÑĥйÑĤе
    -0.15
    IDEO
    -0.15
    egg
    -0.15
    idth
    -0.15
    inkel
    -0.14
    uggage
    -0.14
    POSITIVE LOGITS
    ARRANT
    0.18
    670
    0.16
    ender
    0.16
     Wire
    0.15
    -men
    0.14
     priv
    0.14
    ÑģÑĤеÑĢ
    0.14
    295
    0.14
     chance
    0.14
     wire
    0.14
    Act Density 0.007%

    No Known Activations