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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    the word "may" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.66
    icial
    -0.64
    ging
    -0.63
    ciating
    -0.63
    performing
    -0.62
    feeding
    -0.61
    rieg
    -0.60
    hesive
    -0.59
    enthal
    -0.59
     Composite
    -0.58
    POSITIVE LOGITS
    onna
    0.99
    hap
    0.96
    haps
    0.93
    bes
    0.92
    NF
    0.76
    nard
    0.73
    anners
    0.71
     incent
    0.71
     be
    0.69
    weather
    0.68
    Act Density 0.069%

    No Known Activations