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

    Neuronpedia

    INDEX
    Explanations

    statements or examples about the likelihood or possibility of an event happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate choices or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.68
    PDATE
    -0.63
    mare
    -0.62
     Dragonbound
    -0.62
    WER
    -0.60
    ADVERTISEMENT
    -0.59
     Butterfly
    -0.59
    FREE
    -0.58
     TODAY
    -0.58
     Candidate
    -0.57
    POSITIVE LOGITS
    chard
    1.31
    ifice
    1.11
    nam
    1.06
    ific
    1.05
    chid
    1.02
    acles
    1.00
    acle
    0.99
    acular
    0.95
    Else
    0.91
    nery
    0.91
    Act Density 0.032%

    No Known Activations