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

    Neuronpedia

    INDEX
    Explanations

    adjectives ending in '-ant', '-ish', or '-end'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enthusiasm and exceptional quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLA
    -0.68
     Conway
    -0.67
     Zamb
    -0.62
     enqu
    -0.62
     delivery
    -0.61
     Mayo
    -0.60
     opposed
    -0.59
    querque
    -0.58
     Cheong
    -0.58
     silenced
    -0.57
    POSITIVE LOGITS
    ishly
    1.10
    astical
    1.06
    astic
    1.00
    itious
    0.94
    iman
    0.93
    leness
    0.87
    tails
    0.87
    ish
    0.85
    ini
    0.84
    oms
    0.84
    Act Density 0.117%

    No Known Activations