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

    Neuronpedia

    INDEX
    Explanations

    expressions of doubt or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intptr
    -0.42
     InputDecoration
    -0.38
     terbatas
    -0.38
     deschis
    -0.38
    lapsingToolbar
    -0.37
    verifyException
    -0.36
    bukaan
    -0.36
     boneca
    -0.36
    writeFieldEnd
    -0.36
    vstack
    -0.35
    POSITIVE LOGITS
    ImageContext
    0.57
    URLException
    0.46
    EndContext
    0.46
    WebMethod
    0.45
    تقاوى
    0.44
    帖最后由
    0.43
     createState
    0.41
    ftagPool
    0.40
    CodeAttribute
    0.39
    Vig
    0.39
    Act Density 0.249%

    No Known Activations