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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainity or ambiguity in contexts related to decision-making or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagens
    -0.49
    Storia
    -0.45
    üte
    -0.41
    ️⃣
    -0.40
     PeEnEo
    -0.40
    Autoritní
    -0.40
     hereby
    -0.40
    ValueGenerated
    -0.39
     Tooltip
    -0.39
     zwar
    -0.39
    POSITIVE LOGITS
     something
    1.17
     irgende
    1.16
     somewhere
    1.16
     algún
    1.16
     Somewhere
    1.14
    Somewhere
    1.14
    somewhere
    1.13
     somehow
    1.13
     algum
    1.11
     irgend
    1.09
    Act Density 0.314%

    No Known Activations