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

    Neuronpedia

    INDEX
    Explanations

    mention of the word "Vers" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to treaties and their historical implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.89
    Reviewer
    -0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.70
    UGH
    -0.67
    ħĭ
    -0.65
    olls
    -0.65
    Interstitial
    -0.64
     leukemia
    -0.63
    taboola
    -0.63
    owder
    -0.62
    POSITIVE LOGITS
    atile
    1.33
    atility
    1.28
     Vers
    1.12
     mathemat
    0.94
    Vers
    0.86
     Seym
    0.84
    hip
    0.82
    ions
    0.82
     confir
    0.78
    oit
    0.77
    Act Density 0.002%

    No Known Activations