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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "no more"

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a sense of finality or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irez
    -0.75
    iage
    -0.69
    omnia
    -0.66
    OS
    -0.62
    cius
    -0.61
    worn
    -0.61
    OCK
    -0.61
    erest
    -0.60
    hare
    -0.60
    Psy
    -0.59
    POSITIVE LOGITS
     than
    0.94
     ado
    0.74
    Fake
    0.69
    than
    0.68
     whatsoever
    0.67
     nor
    0.65
     excuses
    0.64
     info
    0.62
    cial
    0.61
     stringent
    0.61
    Act Density 0.034%

    No Known Activations