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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or procedural language

    oai_token-act-pair · gpt-3.5-turbo

    the presence of various symbols or characters that aren't typically found in standard text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indo
    -0.75
    creen
    -0.72
     board
    -0.69
     Marketable
    -0.69
     detached
    -0.69
     couch
    -0.69
     semblance
    -0.69
     constitution
    -0.68
     shroud
    -0.68
     bung
    -0.68
    POSITIVE LOGITS
    ª
    1.25
    ł
    1.20
    ij
    1.07
    Ĵ
    1.03
    ¹
    1.02
    IJ
    0.99
    ¤
    0.98
    £
    0.95
    ¡
    0.95
    ı
    0.94
    Act Density 0.099%

    No Known Activations