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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "see" and its variations, which indicate perception or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cs
    -0.19
    sten
    -0.18
    stp
    -0.17
    eron
    -0.16
    uzzer
    -0.15
    erie
    -0.15
    Ñħо
    -0.15
    ader
    -0.14
    cul
    -0.14
    pper
    -0.14
    POSITIVE LOGITS
    /he
    0.19
     cref
    0.19
    dust
    0.16
     xét
    0.14
    vation
    0.14
    /list
    0.14
    arious
    0.13
    LU
    0.13
    /sm
    0.13
    eof
    0.13
    Act Density 0.142%

    No Known Activations