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

    Neuronpedia

    INDEX
    Explanations

    verbs, especially those related to motion and action

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or political concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reloaded
    -0.69
    Daddy
    -0.63
    Luck
    -0.63
    ALLY
    -0.61
     prematurely
    -0.61
    WT
    -0.60
    Water
    -0.60
    Textures
    -0.60
    Flash
    -0.58
    Cold
    -0.58
    POSITIVE LOGITS
    itud
    1.00
    ande
    0.93
    rique
    0.86
    itent
    0.85
    idas
    0.84
    ó
    0.84
    én
    0.83
    ét
    0.81
    ibli
    0.80
    ici
    0.80
    Act Density 0.209%

    No Known Activations