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

    Neuronpedia

    INDEX
    Explanations

    terms related to questioning or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMPL
    -0.16
    stash
    -0.16
    pedo
    -0.16
    defer
    -0.15
     sacrific
    -0.14
    las
    -0.14
    endors
    -0.14
    _unicode
    -0.14
     è¨
    -0.14
    stration
    -0.14
    POSITIVE LOGITS
    TargetException
    0.19
    /out
    0.18
    orate
    0.15
     Triple
    0.15
     SEN
    0.15
    ãģ£ãģ
    0.15
    idable
    0.15
    uploader
    0.15
    erable
    0.15
     sic
    0.15
    Act Density 0.145%

    No Known Activations