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

    Neuronpedia

    INDEX
    Explanations

    items or phrases that indicate requirements or criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pol
    -0.16
    ÏĦεÏģ
    -0.15
     cop
    -0.15
    ÏĦί
    -0.15
     tw
    -0.14
    çīĪ
    -0.14
    esson
    -0.14
    abler
    -0.14
    ogra
    -0.14
    761
    -0.14
    POSITIVE LOGITS
     Mi
    0.15
    -в
    0.15
    еÑĦ
    0.15
    erdale
    0.14
    ãĥ³ãĥķ
    0.14
    ipse
    0.14
    mî
    0.13
    à¥Ĥड
    0.13
    SYM
    0.13
    -vars
    0.13
    Act Density 0.035%

    No Known Activations