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

    Neuronpedia

    INDEX
    Explanations

    complexity and nuance in discussions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eter
    -0.17
    obel
    -0.16
    shint
    -0.16
    isoft
    -0.15
    оне
    -0.15
     being
    -0.15
    713
    -0.14
    clair
    -0.14
     Eis
    -0.14
    íıIJ
    -0.14
    POSITIVE LOGITS
    ichel
    0.17
    urvey
    0.17
    iffe
    0.16
    AME
    0.15
     unders
    0.15
    ÌĨ
    0.14
    rchive
    0.14
    ма
    0.14
     Wag
    0.14
    BootTest
    0.14
    Act Density 0.010%

    No Known Activations