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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific non-alphanumeric token in the text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or encoding issues in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.67
     Lump
    -0.63
    oteric
    -0.62
    itely
    -0.62
    verts
    -0.60
    ocus
    -0.60
     exorc
    -0.60
    inqu
    -0.59
     Canaver
    -0.58
    added
    -0.57
    POSITIVE LOGITS
     Office
    1.12
     Bever
    0.74
    marks
    0.70
     Engine
    0.69
    ¹
    0.68
    ndra
    0.67
    holm
    0.66
    ezvous
    0.66
    mark
    0.65
    Service
    0.65
    Act Density 0.000%

    No Known Activations