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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressions of sympathy or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expressions of sympathy and public responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brightly
    -0.70
     chronically
    -0.65
     cultured
    -0.64
     unprotected
    -0.63
     volatile
    -0.61
     perpetually
    -0.60
    ensis
    -0.60
     degraded
    -0.59
     stationary
    -0.58
     excessively
    -0.57
    POSITIVE LOGITS
    ocations
    0.75
    gement
    0.68
    ings
    0.66
    autions
    0.65
    isations
    0.64
    gements
    0.64
    abal
    0.64
    IONS
    0.63
    iple
    0.62
    eries
    0.62
    Act Density 0.629%

    No Known Activations