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

    Neuronpedia

    INDEX
    Explanations

    the presence of the article "a" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the beginning of descriptions of various fictional creatures or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sheets
    -0.61
    eworks
    -0.60
     Vaugh
    -0.57
    Events
    -0.56
     accordingly
    -0.54
     appointments
    -0.53
    AUD
    -0.53
    grounds
    -0.53
    external
    -0.53
    AIDS
    -0.53
    POSITIVE LOGITS
     lot
    0.80
     bunch
    0.71
    sexual
    0.70
    uras
    0.69
    venge
    0.66
     nutshell
    0.66
    ird
    0.65
     whopping
    0.65
    eon
    0.63
     glimpse
    0.62
    Act Density 0.445%

    No Known Activations