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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of characters or people mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UNIVERS
    -0.65
     AND
    -0.61
     TRAN
    -0.61
     HELL
    -0.61
     CONTR
    -0.61
     IPM
    -0.59
     subsid
    -0.59
     Aval
    -0.57
     SYSTEM
    -0.57
     compound
    -0.57
    POSITIVE LOGITS
    axter
    1.10
     alike
    1.09
    esson
    0.99
    oliath
    0.88
    sequent
    0.76
    eele
    0.73
    ancel
    0.72
    avia
    0.72
    ilda
    0.72
    obos
    0.71
    Act Density 0.308%

    No Known Activations