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

    Neuronpedia

    INDEX
    Explanations

    ambiguous statements regarding certainty and knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    524
    -0.15
    267
    -0.15
    rzy
    -0.14
    ourd
    -0.14
    ItemAt
    -0.14
    ibold
    -0.14
    анÑĥ
    -0.14
    urdy
    -0.13
    Ìī
    -0.13
    isto
    -0.13
    POSITIVE LOGITS
     unknown
    0.75
    unknown
    0.67
     Unknown
    0.63
    Unknown
    0.60
     unclear
    0.56
    ä¸įçŁ¥éģĵ
    0.55
     UNKNOWN
    0.54
    _unknown
    0.52
     unsure
    0.49
    UNKNOWN
    0.49
    Act Density 0.428%

    No Known Activations