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

    Neuronpedia

    INDEX
    Explanations

    references to vehicle types and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     List
    -0.16
    esel
    -0.16
     cul
    -0.15
     Hermes
    -0.14
     Letter
    -0.14
    hammer
    -0.14
     fed
    -0.14
     ped
    -0.14
    less
    -0.14
    sted
    -0.14
    POSITIVE LOGITS
    ÑĢиÑģ
    0.17
    OKIE
    0.17
    lero
    0.16
    tü
    0.15
    .Atomic
    0.15
    elts
    0.15
    ichier
    0.14
    familia
    0.14
    ınd
    0.14
    ecret
    0.14
    Act Density 0.024%

    No Known Activations