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

    Neuronpedia

    INDEX
    Explanations

    references to actions or instructions related to software and technology

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.82
    ptin
    -0.74
    perse
    -0.69
    jah
    -0.69
    Balt
    -0.68
    utenberg
    -0.66
    arium
    -0.66
    çĶ°
    -0.66
    rums
    -0.65
    Tan
    -0.64
    POSITIVE LOGITS
     behalf
    1.24
     occasion
    1.00
     Linux
    0.94
     desktop
    0.93
     Windows
    0.92
    shore
    0.92
     linux
    0.90
    site
    0.89
    screen
    0.88
     Github
    0.87
    Act Density 0.141%

    No Known Activations