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

    Neuronpedia

    INDEX
    Explanations

    words indicating comparison and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zsche
    -0.16
    ighest
    -0.16
    umbed
    -0.15
     Guidance
    -0.15
    ellar
    -0.14
    ãĤ©
    -0.14
    Gro
    -0.14
    зв
    -0.14
    esModule
    -0.14
    313
    -0.13
    POSITIVE LOGITS
    bul
    0.16
     tele
    0.15
    buffer
    0.15
    estone
    0.14
    yst
    0.14
    jak
    0.14
    unde
    0.14
    rief
    0.14
     et
    0.14
    ocker
    0.13
    Act Density 0.005%

    No Known Activations