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

    Neuronpedia

    INDEX
    Explanations

    words related to measurements of size

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dimensions or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andum
    -0.69
    plet
    -0.65
    zie
    -0.65
    unes
    -0.64
    vernment
    -0.63
     bodily
    -0.63
    OTA
    -0.62
    ovie
    -0.62
    ruption
    -0.60
    ectomy
    -0.60
    POSITIVE LOGITS
     width
    1.19
     Width
    1.09
    width
    1.07
    Width
    0.94
    sheets
    0.86
    ï¸
    0.83
    sd
    0.83
    sheet
    0.82
     actionGroup
    0.82
    pread
    0.79
    Act Density 0.008%

    No Known Activations