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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and expressions of admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ttps
    -0.57
     TextInputType
    -0.55
    ']],
    -0.55
    oredCriteria
    -0.54
     ExecuteAsync
    -0.54
    CAPITULO
    -0.53
    */),
    -0.52
    }}%
    -0.48
    ]<=
    -0.48
     CURIAM
    -0.47
    POSITIVE LOGITS
     awesome
    1.33
     sucks
    1.29
     Awesome
    1.26
     AWESOME
    1.25
    awesome
    1.24
     suck
    1.19
    Awesome
    1.17
    AWESOME
    1.08
     sucked
    0.98
     AMAZING
    0.95
    Act Density 0.227%

    No Known Activations