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

    Neuronpedia

    INDEX
    Explanations

    emoticons or special characters

    oai_token-act-pair · gpt-3.5-turbo

    specific non-standard characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kling
    -0.72
     diffusion
    -0.71
     Berm
    -0.69
     Franch
    -0.68
     Sinai
    -0.68
     recorder
    -0.67
     Manit
    -0.67
     Bain
    -0.63
    krit
    -0.63
     Sinclair
    -0.62
    POSITIVE LOGITS
    Į
    1.70
    Ģ
    1.63
    Ĥ
    1.61
    İ
    1.59
    ¤
    1.58
    ı
    1.57
    į
    1.55
    ¦
    1.53
    Ĩ
    1.52
    IJ
    1.52
    Act Density 0.019%

    No Known Activations