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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating percentages or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    انجليز
    -0.84
     InputDecoration
    -0.74
    glades
    -0.72
     Orrell
    -0.72
    ähkö
    -0.71
     الحره
    -0.70
    PreferredItem
    -0.70
     Andree
    -0.69
    "]="
    -0.67
    }*/
    -0.67
    POSITIVE LOGITS
     ExecuteAsync
    0.71
     flesta
    0.61
     את
    0.59
     Drittel
    0.58
     all
    0.57
     část
    0.57
     každé
    0.57
    <bos>
    0.57
    GroupLayout
    0.57
     Prozent
    0.56
    Act Density 0.145%

    No Known Activations