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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experience and impactful moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adesh
    -0.16
    zos
    -0.15
    ulis
    -0.15
    ниÑĨе
    -0.14
    еÑĩно
    -0.14
    pagen
    -0.14
    thon
    -0.14
    rej
    -0.14
    adf
    -0.14
    aders
    -0.13
    POSITIVE LOGITS
     ever
    0.52
     EVER
    0.39
    -ever
    0.35
    ever
    0.34
     Ever
    0.32
     jamais
    0.31
    Ever
    0.30
     anybody
    0.24
     any
    0.24
    EVER
    0.24
    Act Density 0.035%

    No Known Activations