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

    Neuronpedia

    INDEX
    Explanations

    expressions of thoughts and opinions about decisions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.61
     CreateTagHelper
    -0.61
    SequentialGroup
    -0.56
     Wikimedijinoj
    -0.50
    CloseOperation
    -0.49
    ronpa
    -0.49
    UrlResolution
    -0.47
    aarrggbb
    -0.46
    CheckBreak
    -0.45
    ftagPool
    -0.44
    POSITIVE LOGITS
    AnimationsModule
    0.46
     Banks
    0.38
     Segmentation
    0.36
    Banks
    0.36
     segmentation
    0.35
     ment
    0.34
    以為
    0.34
    Segmentation
    0.34
     espe
    0.34
    以为
    0.33
    Act Density 0.297%

    No Known Activations