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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to various forms of "words" and their influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢава
    -0.15
    ave
    -0.14
    ewood
    -0.14
     lyn
    -0.14
    uild
    -0.14
    ế
    -0.13
     ÑģÑģÑĭл
    -0.13
     Kraft
    -0.13
    llib
    -0.13
    avers
    -0.13
    POSITIVE LOGITS
    ıt
    0.14
     Bakan
    0.14
    jišť
    0.13
     Zuk
    0.13
    _CONVERT
    0.13
     Frid
    0.13
    ÏģÏį
    0.13
     verw
    0.13
    iloc
    0.13
    ème
    0.13
    Act Density 0.018%

    No Known Activations