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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong emotions or convictions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of permanence or lasting memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Newsletter
    -0.80
    illin
    -0.67
    unc
    -0.66
    DIT
    -0.66
    Kin
    -0.65
    iera
    -0.65
    urat
    -0.64
    soType
    -0.61
    MED
    -0.61
    Sequ
    -0.60
    POSITIVE LOGITS
    theless
    1.03
     underestimate
    0.87
     achieve
    0.86
     dream
    0.84
     aspire
    0.82
     tolerate
    0.82
     dreamed
    0.81
     be
    0.80
     attain
    0.80
     EVER
    0.79
    Act Density 0.040%

    No Known Activations