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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    statements related to causes and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     badass
    -0.92
    !'"
    -0.92
     goddamn
    -0.91
    .'"
    -0.91
    ,'"
    -0.85
     yours
    -0.85
    !'
    -0.84
    ?'"
    -0.83
     ain
    -0.81
     marvelous
    -0.79
    POSITIVE LOGITS
     apologised
    1.07
     licences
    1.06
     emphas
    1.04
     analys
    1.01
     recognised
    1.00
     realised
    0.99
     organisers
    0.98
     counselling
    0.98
     organis
    0.96
     organisations
    0.95
    Act Density 0.968%

    No Known Activations