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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing quality or appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.78
    VersionUID
    -0.77
    )•
    -0.77
    )*/
    -0.76
    parsedMessage
    -0.75
    contentLoaded
    -0.75
    Controllo
    -0.75
    ########.
    -0.71
    SBATCH
    -0.71
    ècie
    -0.71
    POSITIVE LOGITS
     looking
    0.65
     looks
    0.54
     looked
    0.54
     look
    0.54
     Looking
    0.53
    look
    0.52
     Looked
    0.51
    re
    0.50
     I
    0.49
    looks
    0.48
    Act Density 0.100%

    No Known Activations