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

    Neuronpedia

    INDEX
    Explanations

    instances of sequential or preparatory actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    but first, but before, but wait

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.51
    ksikon
    -0.49
    providedIn
    -0.48
    InputBorder
    -0.47
    makeText
    -0.47
    GEBURTSDATUM
    -0.47
    jsonwebtoken
    -0.46
     EconPapers
    -0.46
     Theſe
    -0.45
     Wiktionnaire
    -0.45
    POSITIVE LOGITS
    UrlResolution
    0.46
    <bos>
    0.43
     پذ
    0.38
     singlet
    0.37
    さて
    0.37
    pegno
    0.36
     Exor
    0.36
    altri
    0.36
    complexContent
    0.35
     first
    0.35
    Act Density 0.008%

    No Known Activations