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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions related to technology or software

    oai_token-act-pair · gpt-3.5-turbo

    special characters or formatting issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dirt
    -0.73
     torn
    -0.72
    ggies
    -0.71
    lda
    -0.68
     Appalachian
    -0.67
    anwhile
    -0.67
     dstg
    -0.67
    itably
    -0.67
    ctors
    -0.66
     white
    -0.64
    POSITIVE LOGITS
    catentry
    1.03
    ¹
    0.94
    £
    0.92
    º
    0.91
    ¡
    0.89
    ¬
    0.87
    »
    0.85
    Purchase
    0.84
    iversary
    0.83
    ı
    0.82
    Act Density 0.659%

    No Known Activations