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

    Neuronpedia

    INDEX
    Explanations

    references to heavy objects or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.58
    hnia
    -0.58
    发表于
    -0.57
    OGND
    -0.55
     INTERESAR
    -0.54
     trustees
    -0.54
    Hochspringen
    -0.53
    :][
    -0.52
    rozum
    -0.51
    alış
    -0.51
    POSITIVE LOGITS
     Heavy
    1.34
    Heavy
    1.33
     heavy
    1.29
     HEAVY
    1.23
    heavy
    1.21
     heaviest
    1.15
    heav
    1.14
    weights
    1.13
     pesado
    1.03
     Heav
    1.02
    Act Density 0.073%

    No Known Activations