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

    Neuronpedia

    INDEX
    Explanations

    words related to curiosity or interest

    oai_token-act-pair · gpt-3.5-turbo

    expressions of curiosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohm
    -0.76
    ACP
    -0.74
    atra
    -0.65
     Depot
    -0.65
    ayers
    -0.63
    od
    -0.62
    accept
    -0.62
     Physicians
    -0.62
    oan
    -0.62
     Surv
    -0.61
    POSITIVE LOGITS
     curious
    1.20
     curiosity
    1.11
     passers
    0.95
     Curious
    0.87
     onlook
    0.84
    iously
    0.79
    ioned
    0.76
     inqu
    0.76
    edIn
    0.75
     probing
    0.74
    Act Density 0.006%

    No Known Activations