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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating familiarity or existing knowledge of systems or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vfs
    -0.15
     Cous
    -0.15
     Sense
    -0.15
    erras
    -0.14
    alley
    -0.13
    ìĭĿ
    -0.13
    691
    -0.13
    izont
    -0.13
    cox
    -0.13
    ÄĽj
    -0.13
    POSITIVE LOGITS
     already
    0.20
    already
    0.20
     existing
    0.20
    Already
    0.19
     Already
    0.19
    existing
    0.18
    -existing
    0.18
    arkin
    0.17
     sẵn
    0.17
    enberg
    0.16
    Act Density 0.112%

    No Known Activations