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

    Neuronpedia

    INDEX
    Explanations

    concepts related to curiosity and inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    442
    -0.17
    alion
    -0.15
    ati
    -0.15
    hea
    -0.15
    ahl
    -0.15
    ow
    -0.15
    out
    -0.15
     Tie
    -0.15
    497
    -0.14
     Wer
    -0.14
    POSITIVE LOGITS
    ì¡
    0.15
    mong
    0.15
    ously
    0.14
    plr
    0.14
    reamble
    0.14
    RCT
    0.14
    ]={↵
    0.14
    ----------------------------------------------------------------------↵
    0.14
    /assert
    0.14
    ë¡ľìļ´
    0.14
    Act Density 0.018%

    No Known Activations