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

    Neuronpedia

    INDEX
    Explanations

    imperative verbs indicating actions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fy
    -0.16
    ni
    -0.15
    EMS
    -0.14
    foon
    -0.14
    patial
    -0.14
    aoke
    -0.14
    kola
    -0.14
    itta
    -0.14
    )((((
    -0.14
    ditor
    -0.13
    POSITIVE LOGITS
    cket
    0.19
    ork
    0.17
    ze
    0.17
    illet
    0.16
     justice
    0.15
    Sphere
    0.15
     away
    0.15
    _damage
    0.14
    inky
    0.14
    -business
    0.14
    Act Density 0.172%

    No Known Activations