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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to personal achievements or advancements

    oai_token-act-pair · gpt-3.5-turbo

    actions and transitions related to movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Edition
    -0.62
    Drive
    -0.60
     extent
    -0.59
    usra
    -0.59
    twitch
    -0.57
    ocr
    -0.56
    front
    -0.55
    ucks
    -0.54
    orter
    -0.54
     gif
    -0.54
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.85
    redients
    0.84
    itially
    0.69
    ebus
    0.68
    PER
    0.66
    iated
    0.64
     Pengu
    0.64
    ensibly
    0.63
     oneself
    0.62
    ãĤ¢ãĥ«
    0.62
    Act Density 0.262%

    No Known Activations