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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fill" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    styleable
    -0.45
     Règlement
    -0.42
     rubro
    -0.41
    tał
    -0.41
     carte
    -0.40
     protections
    -0.39
     surla
    -0.39
     Szy
    -0.38
     Италијани
    -0.38
     subversion
    -0.37
    POSITIVE LOGITS
     fill
    0.83
     filling
    0.79
     fills
    0.73
     Filling
    0.70
    Filling
    0.68
    filling
    0.67
    fills
    0.64
    CloseOperation
    0.63
     preferred
    0.60
     Fill
    0.54
    Act Density 0.318%

    No Known Activations