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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong personal preferences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion and self-identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     omin
    -0.71
     reper
    -0.70
    çķ
    -0.69
     plantations
    -0.69
     scrimmage
    -0.67
     flourish
    -0.63
    tein
    -0.63
     indefinitely
    -0.62
     appointments
    -0.62
     undermines
    -0.61
    POSITIVE LOGITS
     believer
    0.92
     skept
    0.91
     lucky
    0.90
     skeptical
    0.81
     proud
    0.81
     fortunate
    0.81
     impatient
    0.80
     proponent
    0.79
     obsessed
    0.78
     myself
    0.76
    Act Density 0.302%

    No Known Activations