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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to technical subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.72
    itiz
    -0.67
     dismant
    -0.63
    ipop
    -0.63
    phasis
    -0.63
    ioch
    -0.62
    esis
    -0.61
    andel
    -0.61
    ocracy
    -0.61
     entails
    -0.59
    POSITIVE LOGITS
     respectively
    1.61
     alike
    1.22
     jointly
    1.02
     trademarks
    0.99
     mutually
    0.89
     interchangeable
    0.85
     insepar
    0.85
     intertwined
    0.83
     together
    0.82
    senal
    0.82
    Act Density 0.207%

    No Known Activations