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

    Neuronpedia

    INDEX
    Explanations

    numerical values and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.84
     nakalista
    -0.84
     propOrder
    -0.74
    HasBeenSet
    -0.74
    lynol
    -0.72
    parsedMessage
    -0.71
     _$
    -0.71
    EndGlobalSection
    -0.70
     Exacts
    -0.70
    -0.69
    POSITIVE LOGITS
    tagHelperRunner
    0.76
    1
    0.60
     am
    0.59
     للمعارف
    0.58
    5
    0.56
    8
    0.56
    4
    0.54
    0
    0.54
    2
    0.53
    </thead>
    0.53
    Act Density 0.582%

    No Known Activations