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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating the benefits or consequences of specific actions

    oai_token-act-pair · gpt-3.5-turbo

    statements about benefits or positive effects associated with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cles
    -0.72
    rose
    -0.68
    venants
    -0.67
    Mah
    -0.65
    phant
    -0.64
    $,
    -0.64
    rette
    -0.63
    }{
    -0.62
    sponsored
    -0.62
    Sold
    -0.62
    POSITIVE LOGITS
    geries
    0.98
     purposes
    0.86
    gotten
    0.83
     example
    0.83
    agers
    0.82
     laughs
    0.79
     everybody
    0.77
     detecting
    0.77
     reasons
    0.75
     starters
    0.75
    Act Density 0.087%

    No Known Activations