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

    Neuronpedia

    INDEX
    Explanations

    actions and processes involving physical manipulation or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⎧
    -0.59
     Gor
    -0.47
     Polar
    -0.47
     Na
    -0.46
     نق
    -0.44
    idere
    -0.44
    味
    -0.44
     Wel
    -0.43
    Polar
    -0.42
     Li
    -0.42
    POSITIVE LOGITS
     myſelf
    0.96
     againſt
    0.87
     Monfieur
    0.85
     snippetHide
    0.79
     poffible
    0.79
    帖最后由
    0.78
    expandindo
    0.77
    évaluateur
    0.75
     ſeveral
    0.74
     ſmall
    0.73
    Act Density 0.086%

    No Known Activations