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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "an" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "an"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Things
    -0.74
    bots
    -0.71
     Vaugh
    -0.68
    hood
    -0.67
     Beware
    -0.65
    BLE
    -0.65
    soever
    -0.63
     Functions
    -0.63
    bane
    -0.63
    ï¸
    -0.62
    POSITIVE LOGITS
    esthetic
    0.95
    onym
    0.94
    omal
    0.90
    abolic
    0.89
    agram
    0.86
    ointed
    0.80
    onymous
    0.79
    ormal
    0.75
    omaly
    0.73
    alyses
    0.73
    Act Density 0.207%

    No Known Activations