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

    Neuronpedia

    INDEX
    Explanations

    locations and place names

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azines
    -0.77
     monop
    -0.72
     confir
    -0.69
     Leilan
    -0.69
    rador
    -0.66
     squeeze
    -0.65
     glide
    -0.65
     drift
    -0.64
     Ples
    -0.63
    raint
    -0.62
    POSITIVE LOGITS
    yond
    1.39
    arers
    1.14
    arer
    1.12
    cker
    1.05
    zos
    1.02
    FORE
    0.99
    ards
    0.95
    ech
    0.93
    xt
    0.93
    gotten
    0.92
    Act Density 0.028%

    No Known Activations