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

    Neuronpedia

    INDEX
    Explanations

    phrases that express evidence or demonstration of characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icit
    -0.16
    yte
    -0.15
    icher
    -0.15
    xon
    -0.14
    EDGE
    -0.14
    ÏĨα
    -0.14
    vern
    -0.14
    abit
    -0.14
    еÑĢжав
    -0.14
    ámara
    -0.13
    POSITIVE LOGITS
    orer
    0.16
    enting
    0.15
    azed
    0.15
    engu
    0.14
    outu
    0.14
    _dispatcher
    0.14
    rz
    0.14
     form
    0.14
     perce
    0.14
    angers
    0.14
    Act Density 0.171%

    No Known Activations