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

    Neuronpedia

    INDEX
    Explanations

    specific character sequences or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cord
    -0.16
    olio
    -0.16
    ÑĢаÑħов
    -0.15
    441
    -0.15
    TP
    -0.15
    oria
    -0.15
    μμα
    -0.15
    rtl
    -0.14
    onec
    -0.14
    ÑĨÑĸоналÑĮ
    -0.14
    POSITIVE LOGITS
     white
    0.32
     White
    0.31
     WHITE
    0.28
    white
    0.27
    White
    0.26
    WHITE
    0.26
     whites
    0.24
    _white
    0.24
    -white
    0.24
     Whites
    0.23
    Act Density 0.005%

    No Known Activations