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

    Neuronpedia

    INDEX
    Explanations

    references to people and their identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Италијани
    -0.70
     utafitiHapana
    -0.69
     незавершена
    -0.68
    exitRule
    -0.66
     للاسماء
    -0.63
    RTLR
    -0.60
    __*/
    -0.59
    HideFlags
    -0.59
     jspb
    -0.59
     surla
    -0.58
    POSITIVE LOGITS
     else
    1.52
     ELSE
    0.96
    else
    0.90
     who
    0.85
    Else
    0.82
     Else
    0.81
    ELSE
    0.79
     kto
    0.73
     Nadie
    0.59
     anders
    0.58
    Act Density 0.130%

    No Known Activations