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

    Neuronpedia

    INDEX
    Explanations

    sentences containing the word "what" or phrases that inquire about identity, reasons, or clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    znik
    -0.17
    uster
    -0.16
    USTER
    -0.15
    £p
    -0.14
    _Util
    -0.14
     Newman
    -0.14
    jar
    -0.14
    _drvdata
    -0.14
    Ìģt
    -0.13
    ICTURE
    -0.13
    POSITIVE LOGITS
    anime
    0.14
    placeholders
    0.14
    agenta
    0.14
    à¹īาà¸ĩ
    0.13
    IMER
    0.13
     Mis
    0.13
    /sign
    0.13
     Direction
    0.13
    Mis
    0.13
    mdir
    0.13
    Act Density 0.036%

    No Known Activations