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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance or urgency

    oai_token-act-pair · gpt-3.5-turbo

    the word "is" and its variations to express existence or statements about being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lance
    -0.84
    yip
    -0.69
    sonian
    -0.63
     Blades
    -0.63
    alities
    -0.60
     Moines
    -0.60
     Locations
    -0.58
    uates
    -0.56
    ggles
    -0.55
    imil
    -0.55
    POSITIVE LOGITS
     ever
    1.35
     EVER
    1.22
     spared
    0.94
     immune
    0.94
     remotely
    0.90
     necessarily
    0.90
     harmed
    0.89
    allowed
    0.88
     truly
    0.88
     allowed
    0.83
    Act Density 0.091%

    No Known Activations