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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating self-reflection or self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toy
    -0.16
    bild
    -0.16
    hal
    -0.15
    ë§ī
    -0.15
    lm
    -0.15
     Dahl
    -0.15
    illos
    -0.15
     content
    -0.15
    illas
    -0.14
    content
    -0.14
    POSITIVE LOGITS
    erdale
    0.18
    762
    0.15
    assen
    0.15
    gie
    0.15
    362
    0.15
    -même
    0.14
    ipsis
    0.14
    ker
    0.14
    76
    0.14
    nier
    0.14
    Act Density 0.053%

    No Known Activations