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

    Neuronpedia

    INDEX
    Explanations

    formal statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of formal declarations or statements of regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quir
    -0.77
     nodd
    -0.72
     stuff
    -0.72
     trailed
    -0.70
     Slug
    -0.68
     mound
    -0.67
    )?
    -0.65
    chemy
    -0.64
    toggle
    -0.63
     frowned
    -0.63
    POSITIVE LOGITS
     hereby
    1.19
    sic
    0.93
    Statement
    0.92
     regrett
    0.82
    âĢİ
    0.79
    %"
    0.79
     herein
    0.78
     lawful
    0.77
    Tonight
    0.77
     [-
    0.77
    Act Density 1.521%

    No Known Activations