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

    Neuronpedia

    INDEX
    Explanations

    concepts related to design processes and engineering involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    classed
    -0.15
    cko
    -0.15
    oure
    -0.15
    orthy
    -0.14
     Carpet
    -0.14
    idis
    -0.14
    ema
    -0.13
     carniv
    -0.13
    annis
    -0.13
    igkeit
    -0.13
    POSITIVE LOGITS
    vyk
    0.15
    abus
    0.15
     Vul
    0.14
     Sheldon
    0.14
    hoff
    0.13
    aroo
    0.13
    uyu
    0.13
    aepernick
    0.13
    .pad
    0.13
     Norman
    0.13
    Act Density 0.115%

    No Known Activations