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

    Neuronpedia

    INDEX
    Explanations

    phrases related to issuing statements, alerts, endorsements, apologies, and warnings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "issue" and its variations related to issuing statements, warnings, or alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hov
    -0.90
    uncture
    -0.80
    ovies
    -0.79
    glomer
    -0.73
    ources
    -0.72
    glers
    -0.70
     similarities
    -0.70
    vantage
    -0.68
    antry
    -0.68
    ðĿ
    -0.67
    POSITIVE LOGITS
     apology
    1.28
     statement
    1.25
     Statement
    1.25
     proclamation
    1.20
     warning
    1.18
     ult
    1.07
     summons
    1.07
     apologies
    1.05
     directive
    1.05
    warning
    1.04
    Act Density 0.123%

    No Known Activations