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

    Neuronpedia

    INDEX
    Explanations

    linguistic terms

    oai_token-act-pair · gpt-3.5-turbo

    gerund and participial forms of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raviolet
    -0.75
    ij士
    -0.73
    ĻĤ
    -0.73
     Seym
    -0.69
    IFIED
    -0.68
    Ô
    -0.65
     citiz
    -0.63
     intervening
    -0.62
    Filename
    -0.62
    -+-+
    -0.61
    POSITIVE LOGITS
    ttes
    1.01
    worth
    1.01
    heed
    0.97
    bury
    0.93
    ham
    0.90
    bian
    0.89
    tons
    0.89
    down
    0.87
    gren
    0.86
    gling
    0.86
    Act Density 0.051%

    No Known Activations