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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses or similar punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    330
    -0.16
    æŃ
    -0.16
    hind
    -0.15
    863
    -0.15
    áºŃp
    -0.15
    tos
    -0.14
    ilon
    -0.14
    bersome
    -0.14
    à¹ģส
    -0.14
    žÃŃ
    -0.14
    POSITIVE LOGITS
    LLL
    0.15
    /runtime
    0.15
     à¤ķरव
    0.15
    slaught
    0.13
     Ta
    0.13
     anybody
    0.13
    coli
    0.13
     contr
    0.13
    rem
    0.13
     CUT
    0.13
    Act Density 0.004%

    No Known Activations