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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or points of interest

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "at."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itably
    -0.76
    pex
    -0.73
    ividual
    -0.71
    ufact
    -0.69
    rastructure
    -0.66
     withd
    -0.65
    ulk
    -0.64
    anmar
    -0.63
    ibliography
    -0.63
    mercial
    -0.62
    POSITIVE LOGITS
     at
    1.79
     At
    0.97
    at
    0.93
    At
    0.93
     AT
    0.91
     anywhere
    0.74
     in
    0.69
     during
    0.68
     on
    0.68
     @
    0.67
    Act Density 0.179%

    No Known Activations