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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases indicating beliefs, assumptions, and interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -regexp
    -0.16
    FU
    -0.15
     æ¡
    -0.14
    æŁĦ
    -0.14
    icher
    -0.14
    yro
    -0.13
    usz
    -0.13
    xFFFFFFFF
    -0.13
    -variable
    -0.13
    chein
    -0.13
    POSITIVE LOGITS
    áž
    0.15
    çĦ¶
    0.15
    egas
    0.15
    gren
    0.14
    ovsky
    0.14
    ánÃŃ
    0.14
    irse
    0.14
     lips
    0.14
     swe
    0.14
    anda
    0.14
    Act Density 0.159%

    No Known Activations