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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing a high degree of quality or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrubs
    -0.78
    1
    -0.70
    0
    -0.68
     Вікіпе
    -0.68
     Vog
    -0.66
     scrub
    -0.65
     brû
    -0.64
     Mabel
    -0.64
     spacers
    -0.64
    ubation
    -0.63
    POSITIVE LOGITS
    highly
    1.36
     highly
    1.35
    Highly
    1.29
     Highly
    1.28
     altamente
    0.96
    InitStruct
    0.87
    angliski
    0.85
    andowski
    0.83
     greatly
    0.83
     strongly
    0.80
    Act Density 0.115%

    No Known Activations