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

    Neuronpedia

    INDEX
    Explanations

    references to significant societal or legal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onte
    -0.17
    quet
    -0.17
    anca
    -0.16
    usch
    -0.15
    aft
    -0.15
    ucha
    -0.14
    Handled
    -0.14
    otty
    -0.14
     Ñħод
    -0.14
    )((((
    -0.14
    POSITIVE LOGITS
    tractor
    0.15
    axies
    0.14
     Trib
    0.13
     Gauss
    0.13
     Loud
    0.13
    ivan
    0.13
    ypes
    0.13
    ecome
    0.13
     Golden
    0.13
    phia
    0.13
    Act Density 0.005%

    No Known Activations