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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to artistic evaluation and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.08
     myſelf
    -0.91
     raiſ
    -0.88
     himſelf
    -0.84
     purpoſe
    -0.81
     ſtate
    -0.81
     Reſ
    -0.80
     Theſe
    -0.80
     auffi
    -0.79
     houſe
    -0.79
    POSITIVE LOGITS
     truly
    0.49
    true
    0.47
    B
    0.47
     quality
    0.46
     true
    0.44
    lik
    0.42
    truly
    0.42
     B
    0.41
    ⓘ
    0.41
    Ordinary
    0.41
    Act Density 0.312%

    No Known Activations