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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific events or locations

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating location or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategory
    -0.82
    heastern
    -0.75
    icularly
    -0.73
    hement
    -0.72
    some
    -0.71
    ifax
    -0.68
     secondly
    -0.67
    selage
    -0.67
    antine
    -0.66
     consecut
    -0.66
    POSITIVE LOGITS
     Addiction
    0.95
     Motion
    0.93
     Thrones
    0.92
     Aging
    0.91
     Wonderland
    0.90
     Progress
    0.90
     Humanity
    0.88
     Depth
    0.87
     Poverty
    0.85
     Crisis
    0.84
    Act Density 0.181%

    No Known Activations