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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibrary
    -0.63
    ELF
    -0.62
     Breed
    -0.62
    igm
    -0.61
    ĸļ
    -0.61
    zac
    -0.60
     Shutterstock
    -0.60
    Ĥ¬
    -0.60
    igate
    -0.60
    rican
    -0.59
    POSITIVE LOGITS
     accordingly
    1.15
     alike
    1.08
     thereafter
    0.91
     consequently
    0.89
     therein
    0.86
     thereof
    0.82
     thereto
    0.81
     versa
    0.77
     refuses
    0.70
     agrees
    0.70
    Act Density 0.463%

    No Known Activations