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

    Neuronpedia

    INDEX
    Explanations

    phrases related to analyzing and discussing behavior or actions of individuals

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases and behavioral assessments of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concludes
    -0.72
    orthy
    -0.63
     EDITION
    -0.62
     Investigators
    -0.61
     underscores
    -0.61
     licens
    -0.60
     Shap
    -0.59
     Gutenberg
    -0.59
     illustration
    -0.58
     listings
    -0.58
    POSITIVE LOGITS
     sul
    0.87
     pissed
    0.87
     annoyed
    0.82
     fucked
    0.81
     messed
    0.80
     noticeably
    0.80
     goof
    0.79
     stubborn
    0.78
     behaved
    0.77
     kinda
    0.77
    Act Density 0.903%

    No Known Activations