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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.15
    minating
    -0.14
    mand
    -0.14
    392
    -0.14
    asto
    -0.13
    ãĥ³ãĥĢ
    -0.13
     tranh
    -0.13
    æŃ
    -0.13
    473
    -0.13
     sniff
    -0.13
    POSITIVE LOGITS
    velt
    0.16
    Ấ
    0.16
    ennen
    0.15
     é¤
    0.15
    itary
    0.14
    REEN
    0.14
    erta
    0.13
    IGHL
    0.13
    ierarchy
    0.13
    utron
    0.13
    Act Density 0.136%

    No Known Activations