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

    Neuronpedia

    INDEX
    Explanations

    large activation values representing separate sections or segments in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.62
    IsMutable
    -0.62
    SourceChecksum
    -0.59
     للمعارف
    -0.57
     Winaray
    -0.55
    permum
    -0.55
    ſelves
    -0.54
     števil
    -0.54
     invokingState
    -0.53
    Externé
    -0.52
    POSITIVE LOGITS
    apimachinery
    0.73
     name
    0.68
     getName
    0.65
    名称
    0.63
     names
    0.61
     Name
    0.60
    name
    0.60
     NAME
    0.59
     नाम
    0.57
    getName
    0.54
    Act Density 0.142%

    No Known Activations