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

    Neuronpedia

    INDEX
    Explanations

    content related to comparisons and distinctions in performance or characteristics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    lapsingToolbar
    -0.72
     Roskov
    -0.60
    AddHtmlAttribute
    -0.60
    itonitis
    -0.59
     skier
    -0.58
    GrantedAuthority
    -0.58
    Hauptartikel
    -0.57
    MLLoader
    -0.56
    esModule
    -0.56
    \{\\
    -0.55
    POSITIVE LOGITS
     than
    1.40
     niż
    0.99
    than
    0.92
     daripada
    0.92
     Than
    0.91
     kuin
    0.90
    Than
    0.85
     THAN
    0.84
     än
    0.81
     decât
    0.72
    Act Density 0.453%

    No Known Activations