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

    Neuronpedia

    INDEX
    Explanations

    phrases or sequences of characters preceded by specific symbols

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     detached
    -0.73
     guiActiveUnfocused
    -0.72
     bung
    -0.68
     shroud
    -0.67
     obscurity
    -0.67
     Mirage
    -0.66
     dividing
    -0.65
     descending
    -0.65
     division
    -0.65
    creen
    -0.65
    POSITIVE LOGITS
    ł
    1.25
    ¹
    1.14
    ONSORED
    1.07
    IJ
    1.03
    ij
    0.96
    ı
    0.93
    £
    0.91
    Į
    0.90
    ª
    0.90
    Ĵ
    0.89
    Act Density 0.150%

    No Known Activations