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

    Neuronpedia

    INDEX
    Explanations

    sentences related to self-reflection and personal growth

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cartel
    -0.75
     ratified
    -0.74
     sacked
    -0.71
     himself
    -0.70
     marching
    -0.70
     Urug
    -0.68
     gunfire
    -0.68
     consulate
    -0.68
     inaug
    -0.67
     embassy
    -0.67
    POSITIVE LOGITS
    Example
    1.22
    Examples
    1.15
    Avoid
    1.13
    Conclusion
    1.09
    Sometimes
    1.08
    Learn
    1.07
    VERTISEMENT
    1.04
    Often
    1.04
    If
    1.03
    pmwiki
    1.02
    Act Density 0.657%

    No Known Activations