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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authorship and candidacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.91
    ArrowToggle
    -0.74
     arşivlendi
    -0.73
    +#+#
    -0.67
    EndContext
    -0.65
    FunctionFlags
    -0.65
    djangoproject
    -0.65
     snippetHide
    -0.62
     EconPapers
    -0.61
     بخوانید
    -0.58
    POSITIVE LOGITS
    esterday
    0.53
    phalt
    0.53
     marinho
    0.52
     Yiddish
    0.49
    AutoScaleMode
    0.49
     Vantage
    0.48
     cata
    0.47
     
    0.47
     hendes
    0.47
    cotta
    0.46
    Act Density 0.272%

    No Known Activations