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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a basis or foundation for statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     excuse
    -0.14
     Flour
    -0.13
    zsche
    -0.13
    odb
    -0.13
    iture
    -0.13
    thal
    -0.13
    èĦ
    -0.13
    ¼
    -0.13
    az
    -0.13
     extras
    -0.13
    POSITIVE LOGITS
     upon
    0.24
    upon
    0.20
     Upon
    0.17
    nard
    0.17
    64
    0.16
    ddy
    0.16
    adesh
    0.16
    -base
    0.16
    .Base
    0.15
    elik
    0.15
    Act Density 0.030%

    No Known Activations