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

    Neuronpedia

    INDEX
    Explanations

    references to codes of conduct or ethical guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.16
    tes
    -0.14
    /tiny
    -0.14
    =Value
    -0.14
    aha
    -0.14
     ust
    -0.14
    stab
    -0.14
    ugh
    -0.14
     Stub
    -0.13
     ÑĥÑģл
    -0.13
    POSITIVE LOGITS
    mdl
    0.20
    ument
    0.17
    836
    0.15
    upe
    0.14
    hou
    0.14
     Kou
    0.14
    pons
    0.14
    ADC
    0.14
    ery
    0.14
     ent
    0.13
    Act Density 0.042%

    No Known Activations