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

    Neuronpedia

    INDEX
    Explanations

    special characters or non-English word fragments

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clo
    -0.66
     bil
    -0.63
     Vinyl
    -0.62
     spending
    -0.62
     CC
    -0.61
     die
    -0.60
     CGI
    -0.59
     CF
    -0.59
     DC
    -0.59
     Da
    -0.59
    POSITIVE LOGITS
    §
    4.49
    ¨
    1.94
    ¦
    1.86
    ¢
    1.81
    ©
    1.81
    ¥
    1.80
    «
    1.74
    ĩ
    1.74
    Ĺ
    1.74
    ª
    1.73
    Act Density 0.010%

    No Known Activations