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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences with reported speech or quotes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shroud
    -0.78
     coerc
    -0.72
     conversions
    -0.72
    creen
    -0.71
     assemb
    -0.69
     conspiracy
    -0.68
     dispers
    -0.68
     representation
    -0.68
     semblance
    -0.68
     airs
    -0.67
    POSITIVE LOGITS
    ľ
    1.60
    ł
    1.57
    ª
    1.56
    IJ
    1.46
    ¡
    1.45
    ij
    1.43
    Ĵ
    1.39
    ¦
    1.37
    Ķ
    1.37
    ¤
    1.35
    Act Density 0.085%

    No Known Activations