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

    Neuronpedia

    INDEX
    Explanations

    the presence of structure or format in written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tap
    -0.59
     taps
    -0.54
    ers
    -0.53
    ation
    -0.50
    les
    -0.49
    és
    -0.49
    zeit
    -0.48
    ations
    -0.48
    天下
    -0.47
    座
    -0.46
    POSITIVE LOGITS
    RetentionPolicy
    0.79
     itſelf
    0.78
     onOptions
    0.77
    alyptus
    0.75
     ModelExpression
    0.72
    </thead>
    0.71
    moiselle
    0.69
     themſelves
    0.69
    ilibrium
    0.67
     Anfänger
    0.67
    Act Density 0.105%

    No Known Activations