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

    Neuronpedia

    INDEX
    Explanations

    words related to famous individuals' names that overlap with other words

    oai_token-act-pair · gpt-3.5-turbo

    names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.79
    ãĥ´
    -0.79
     inval
    -0.70
    adelphia
    -0.68
    gments
    -0.67
    ãĤ¶
    -0.66
    ilitarian
    -0.63
    ãĥĺ
    -0.63
     Sask
    -0.63
     ����
    -0.63
    POSITIVE LOGITS
    igham
    0.75
    ski
    0.73
     regimes
    0.70
    rake
    0.68
    inson
    0.67
    iola
    0.66
     Bentley
    0.65
    oÄŁ
    0.65
    interstitial
    0.65
    styles
    0.64
    Act Density 0.018%

    No Known Activations