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

    Neuronpedia

    INDEX
    Explanations

    information related to offers, promotions, and optional actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "may" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ging
    -0.77
     Fighter
    -0.73
     Composite
    -0.70
     Bagg
    -0.69
    ãĥ¼ãĥ«
    -0.64
    raphic
    -0.63
    hran
    -0.61
    killer
    -0.60
    performing
    -0.60
    isu
    -0.60
    POSITIVE LOGITS
    hap
    1.07
    haps
    1.00
    onna
    0.99
    nard
    0.96
     optionally
    0.80
    adian
    0.79
     misunder
    0.77
    weather
    0.75
    bes
    0.75
    entimes
    0.75
    Act Density 0.077%

    No Known Activations