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

    Neuronpedia

    INDEX
    Explanations

    email-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the indefinite articles "a" and "an"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indign
    -0.79
    forth
    -0.75
     appell
    -0.71
    Ont
    -0.68
    offic
    -0.68
    external
    -0.68
     optics
    -0.67
    agents
    -0.67
     eg
    -0.67
    Catal
    -0.66
    POSITIVE LOGITS
     couple
    0.92
    uras
    0.89
     guest
    0.86
     friend
    0.86
     lot
    0.86
     bunch
    0.84
     few
    0.81
     handful
    0.77
     glimpse
    0.76
    uctions
    0.75
    Act Density 0.287%

    No Known Activations