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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Wigs" with various levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and entities with the last name "Wein" and variations, as well as elements related to wigs and shacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Duc
    -0.71
    WAYS
    -0.62
    theless
    -0.62
     Freem
    -0.62
    hovah
    -0.60
    iosyn
    -0.59
     synchron
    -0.58
     Moor
    -0.58
     Gujarat
    -0.57
    rontal
    -0.57
    POSITIVE LOGITS
    glers
    1.29
    poon
    1.10
    manship
    1.01
    nikov
    0.99
    ource
    0.98
    poons
    0.95
    ongs
    0.95
    boro
    0.93
    hiba
    0.90
    itute
    0.90
    Act Density 0.017%

    No Known Activations