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

    Neuronpedia

    INDEX
    Explanations

    questions or statements expressing uncertainty or the need to gather more information

    oai_token-act-pair · gpt-3.5-turbo

    statements of uncertainty or knowledge limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.58
    rin
    -0.58
    plex
    -0.58
    alia
    -0.57
    jet
    -0.57
    TN
    -0.56
    ctory
    -0.56
    leted
    -0.56
    ciating
    -0.56
     Parad
    -0.55
    POSITIVE LOGITS
     definitively
    1.21
     anymore
    1.15
     whether
    1.06
     exactly
    1.05
     accurately
    1.04
     precisely
    0.98
     nor
    0.98
     exact
    0.95
     precise
    0.95
     anything
    0.94
    Act Density 0.199%

    No Known Activations