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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghed
    -0.56
    argout
    -0.55
    клопе
    -0.49
    duled
    -0.49
    imum
    -0.48
    itions
    -0.47
    ohol
    -0.46
    kling
    -0.46
    ruary
    -0.46
    cipal
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.57
     feroit
    0.55
     tetrachloride
    0.55
     quæ
    0.55
    Slf
    0.54
     uova
    0.54
     Informações
    0.54
     blessé
    0.54
     _('
    0.54
    ütün
    0.54
    Act Density 0.269%

    No Known Activations