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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosyncr
    -0.79
    ktop
    -0.75
    iterranean
    -0.70
    Planet
    -0.70
    ondon
    -0.64
    ospace
    -0.63
    racuse
    -0.62
    Ess
    -0.62
    roads
    -0.61
    ffer
    -0.60
    POSITIVE LOGITS
     they
    0.96
    phy
    0.96
     usual
    0.91
     if
    0.91
     soon
    0.90
     he
    0.89
    bestos
    0.86
     opposed
    0.84
     she
    0.84
     instructed
    0.83
    Act Density 0.123%

    No Known Activations