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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "report" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èı¯
    -0.17
    uke
    -0.17
    erner
    -0.16
    akh
    -0.15
    ico
    -0.15
    lesen
    -0.15
     Gerald
    -0.14
    nero
    -0.14
     Source
    -0.14
     source
    -0.14
    POSITIVE LOGITS
    ILT
    0.16
    ImageContext
    0.16
    phans
    0.15
    tin
    0.15
    곤
    0.15
    bole
    0.15
    aris
    0.15
    $/,
    0.14
    olley
    0.14
    bis
    0.14
    Act Density 0.025%

    No Known Activations