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

    Neuronpedia

    INDEX
    Explanations

    uppercase letters followed by either a period or a space

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'S'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.68
    lehem
    -0.63
     overboard
    -0.61
    grave
    -0.61
    illion
    -0.60
     mathemat
    -0.59
    kered
    -0.59
    ERAL
    -0.58
     encour
    -0.57
    dn
    -0.57
    POSITIVE LOGITS
     S
    2.96
    S
    1.74
     s
    1.52
     SA
    1.28
     SV
    1.23
     Si
    1.19
     SQ
    1.13
     SM
    1.08
     N
    1.08
     SE
    1.08
    Act Density 0.037%

    No Known Activations