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

    Neuronpedia

    INDEX
    Explanations

    words related to tracking progress or updates on a situation

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of the pronoun "we."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.75
    interstitial
    -0.68
     Kurd
    -0.64
    à
    -0.63
    ĸļ
    -0.63
    Reviewer
    -0.62
    uces
    -0.62
    advertisement
    -0.58
    Joined
    -0.56
    comes
    -0.56
    POSITIVE LOGITS
    'll
    1.47
     intend
    1.41
     anticipate
    1.36
    're
    1.25
     plan
    1.21
     haven
    1.19
     expect
    1.18
     will
    1.18
     hope
    1.15
    've
    1.11
    Act Density 0.281%

    No Known Activations