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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to dissatisfaction or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases expressing disapproval or condemnation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iago
    -0.84
    roots
    -0.75
    estones
    -0.74
    ifting
    -0.74
    izations
    -0.74
    itudes
    -0.74
    itar
    -0.73
    ana
    -0.72
    estone
    -0.71
    agne
    -0.70
    POSITIVE LOGITS
     disappro
    0.92
     disapproval
    0.83
    Rating
    0.76
     disapprove
    0.74
     cens
    0.73
     frown
    0.70
     glare
    0.70
     barking
    0.70
     aback
    0.70
     shy
    0.68
    Act Density 0.021%

    No Known Activations