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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of HTML headers in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MethodManager
    -0.53
    UnknownFieldSet
    -0.51
    feinander
    -0.49
     
    -0.48
    ウム
    -0.47
     see
    -0.46
    tableFuture
    -0.46
     sich
    -0.44
     et
    -0.44
     Ak
    -0.44
    POSITIVE LOGITS
    head
    2.23
    HEAD
    1.93
    heads
    1.66
    Head
    1.55
     HEAD
    1.43
     Head
    1.25
    ヘッド
    1.17
    Heads
    1.04
    headed
    1.04
    heading
    1.01
    Act Density 0.161%

    No Known Activations