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

    Neuronpedia

    INDEX
    Explanations

    active verbs and actions, particularly those that indicate doing or performing distinct tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jac
    -0.17
    ingen
    -0.15
    ip
    -0.14
    /catalog
    -0.14
    ousse
    -0.14
    bat
    -0.13
    inded
    -0.13
    ÙıÙĨ
    -0.13
    hausen
    -0.13
    bell
    -0.13
    POSITIVE LOGITS
    ifestyles
    0.19
     duty
    0.17
    вÑĸ
    0.15
    instr
    0.14
    ideos
    0.14
    eka
    0.14
    ost
    0.14
    teil
    0.14
     Duty
    0.14
     STATS
    0.14
    Act Density 0.020%

    No Known Activations