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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo

    the word "ale" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nl
    -0.87
    ness
    -0.78
    nesses
    -0.75
    soDeliveryDate
    -0.71
    staff
    -0.70
     Beir
    -0.63
    ulates
    -0.62
    ingen
    -0.62
    liness
    -0.61
    NESS
    -0.61
    POSITIVE LOGITS
    cki
    1.19
    uca
    1.13
    xit
    1.11
    ppo
    1.05
    ño
    0.93
    ttes
    0.93
    ea
    0.92
    jandro
    0.85
    lla
    0.85
    ISTER
    0.83
    Act Density 0.058%

    No Known Activations