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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identity and self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Signalez
    -0.39
    libft
    -0.35
     geçir
    -0.35
    ViewFeatures
    -0.34
     Italijanski
    -0.33
    Климат
    -0.33
    TintMode
    -0.33
    scriptcase
    -0.32
    Šaltiniai
    -0.32
    Autoritní
    -0.31
    POSITIVE LOGITS
     going
    3.25
    Going
    2.44
    going
    2.34
     GOING
    2.31
     Going
    2.27
     gonna
    2.23
    GOING
    1.83
     GONNA
    1.73
     Gonna
    1.69
    gonna
    1.69
    Act Density 0.480%

    No Known Activations