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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.99
    \"");
    -0.99
    رشف
    -0.94
    ContentAsync
    -0.94
     avoient
    -0.94
     '\\;'
    -0.90
    WarningLevel
    -0.88
    UnsafeEnabled
    -0.88
    Personendaten
    -0.87
    RectangleBorder
    -0.86
    POSITIVE LOGITS
    nix
    0.45
    inv
    0.44
    ater
    0.43
    トン
    0.43
     kef
    0.42
     receipt
    0.42
     agu
    0.42
    …
    0.40
     Inv
    0.40
    даго
    0.39
    Act Density 0.078%

    No Known Activations