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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recommendations or endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    strong positive recommendations or endorsements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    TagMode
    -0.43
    SourceChecksum
    -0.39
    AnimationsModule
    -0.35
    findpost
    -0.35
    вость
    -0.34
     مه
    -0.34
    FFIX
    -0.33
     heng
    -0.33
     disambiguazione
    -0.31
    HXLINE
    -0.31
    POSITIVE LOGITS
     recommendation
    3.16
     recommended
    3.03
     recommendations
    3.02
     recommend
    2.89
     recommending
    2.73
     Recommendation
    2.69
     recommends
    2.67
     Recommendations
    2.63
    recommended
    2.61
    recommendation
    2.59
    Act Density 0.551%

    No Known Activations