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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating prior statements or references made in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.17
    hausen
    -0.15
     travers
    -0.15
     vag
    -0.14
     Ethnic
    -0.13
    ContentPane
    -0.13
    etter
    -0.13
    oci
    -0.13
     Greater
    -0.13
    rib
    -0.13
    POSITIVE LOGITS
    foy
    0.16
    .Factory
    0.15
    -Men
    0.15
    [assembly
    0.14
    mad
    0.14
    nge
    0.14
    adık
    0.14
    kul
    0.14
    øre
    0.14
    TOT
    0.14
    Act Density 0.048%

    No Known Activations