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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to physical activities involving body movements

    oai_token-act-pair · gpt-3.5-turbo

    connections and interactions between actions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.86
     citiz
    -0.85
    miah
    -0.81
    ufact
    -0.78
    etus
    -0.72
    ©¶æ¥µ
    -0.71
    inosaur
    -0.68
    ylum
    -0.68
     Evangel
    -0.68
    elfare
    -0.67
    POSITIVE LOGITS
    ï¸ı
    0.88
     yarn
    0.79
     arrows
    0.77
    Rot
    0.75
     Arrows
    0.74
     paddle
    0.71
    pload
    0.70
    twitch
    0.67
     sting
    0.66
    izont
    0.66
    Act Density 0.841%

    No Known Activations