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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identity and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    typename
    -0.50
    UBLE
    -0.46
    团
    -0.45
    cedure
    -0.45
    世纪
    -0.44
    omla
    -0.43
    Means
    -0.43
    彼女は
    -0.43
     autorytatywna
    -0.42
    introduction
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.82
     الحره
    0.77
    Tembelea
    0.72
    writeFieldEnd
    0.70
     utafitiHapana
    0.68
     ujednoznacz
    0.66
     offline
    0.65
     Offline
    0.63
    StoryboardSegue
    0.62
     CreateTagHelper
    0.59
    Act Density 0.228%

    No Known Activations