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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific names or identifiers associated with individuals, organizations, or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resil
    -0.82
     Contra
    -0.79
    309
    -0.79
    soType
    -0.76
     Fairfax
    -0.74
     Weinstein
    -0.73
     Niger
    -0.72
     understatement
    -0.71
    ItemTracker
    -0.71
     Rousse
    -0.71
    POSITIVE LOGITS
    K
    1.44
    k
    1.40
    KC
    1.36
    KS
    1.33
    ks
    1.32
     KE
    1.31
    KK
    1.29
    KE
    1.28
     KD
    1.27
    KA
    1.27
    Act Density 0.515%

    No Known Activations