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

    Neuronpedia

    INDEX
    Explanations

    terms related to the complexity or simplicity of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apol
    -0.16
    glob
    -0.16
    gratis
    -0.15
    [email
    -0.14
     INCIDENT
    -0.14
    ulfilled
    -0.14
    .quick
    -0.14
    åŃĿ
    -0.13
    ìĶ
    -0.13
    orsche
    -0.13
    POSITIVE LOGITS
    isque
    0.17
    lund
    0.16
    ublik
    0.15
    į°
    0.14
    attention
    0.14
    iko
    0.14
    asley
    0.14
    DRV
    0.14
     Locator
    0.14
    ιο
    0.14
    Act Density 0.051%

    No Known Activations