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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve evaluation or critique of various subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating attribution or evaluation of actions and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hole
    -0.73
    hello
    -0.72
     endif
    -0.70
    vantage
    -0.69
    holes
    -0.67
    CNN
    -0.65
    cape
    -0.64
    hog
    -0.63
    haven
    -0.62
     laughed
    -0.61
    POSITIVE LOGITS
     unprecedented
    0.79
    erity
    0.76
    illet
    0.73
     Catal
    0.71
    Detailed
    0.67
     customary
    0.67
    mbuds
    0.65
    QL
    0.64
     Baird
    0.64
     Calder
    0.64
    Act Density 0.395%

    No Known Activations