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

    Neuronpedia

    INDEX
    Explanations

    strong affirmations or denials, indicating opinions or feelings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    op
    -0.40
    …
    -0.39
    ds
    -0.39
    the
    -0.38
    rin
    -0.38
     waiting
    -0.37
    ~
    -0.37
     vex
    -0.37
     being
    -0.36
    za
    -0.35
    POSITIVE LOGITS
    TagMode
    1.07
    Cyfeiriadau
    0.98
    tvguidetime
    0.93
     typelib
    0.93
    RectangleBorder
    0.91
    zzleHttp
    0.91
    Lähteet
    0.90
    CodeAttribute
    0.88
    دانشنامهٔ
    0.86
     EconPapers
    0.85
    Act Density 0.074%

    No Known Activations