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

    Neuronpedia

    INDEX
    Explanations

    significant changes or transformations from one state to another

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating transitions or changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įåĸļ士
    -0.86
    QUI
    -0.76
    Enlarge
    -0.75
    jong
    -0.73
    SPONSORED
    -0.72
    iosyn
    -0.70
    Likewise
    -0.68
    Ãį
    -0.67
    DAQ
    -0.65
    tracks
    -0.65
    POSITIVE LOGITS
     obscurity
    0.96
     afar
    0.79
     humble
    0.78
     mildly
    0.76
     conception
    0.73
     hating
    0.71
     lowly
    0.71
     bland
    0.71
     novice
    0.70
     dormant
    0.69
    Act Density 0.069%

    No Known Activations