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

    Neuronpedia

    INDEX
    Explanations

    technical information about data handling and processing

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert the existence or state of data and its characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.83
    osate
    -0.80
    ionics
    -0.67
    alities
    -0.66
    Others
    -0.65
    worthiness
    -0.64
    atives
    -0.63
    endon
    -0.62
    doms
    -0.61
    irm
    -0.60
    POSITIVE LOGITS
     indistinguishable
    1.12
     treated
    1.08
     supposed
    1.06
     usually
    1.03
    omorphic
    1.01
     stored
    0.98
     represented
    0.98
     ALWAYS
    0.97
     assumed
    0.97
     always
    0.96
    Act Density 0.324%

    No Known Activations