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

    Neuronpedia

    INDEX
    Explanations

    specific aspects within a context or subject

    oai_token-act-pair · gpt-3.5-turbo

    references to various facets or components of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ander
    -0.72
    raid
    -0.71
    sil
    -0.65
    nesia
    -0.65
    ================
    -0.61
     gasp
    -0.60
    andering
    -0.58
    asu
    -0.58
    christ
    -0.58
    gently
    -0.58
    POSITIVE LOGITS
     aspects
    1.13
     facets
    0.99
     guiActiveUn
    0.82
     elements
    0.79
     thereof
    0.78
     similarities
    0.78
    itives
    0.77
    etter
    0.77
    afety
    0.76
    models
    0.75
    Act Density 0.014%

    No Known Activations