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

    Neuronpedia

    INDEX
    Explanations

    strings related to fiscal years and specific names ending with "Roh6"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fiscal years and specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     totem
    -0.71
    slave
    -0.71
     suff
    -0.70
     Norn
    -0.69
    Uk
    -0.69
    Car
    -0.67
     Orthodox
    -0.67
    ilver
    -0.64
     emptiness
    -0.63
    REF
    -0.63
    POSITIVE LOGITS
     FY
    2.42
     KP
    2.13
     Roh
    1.97
     KH
    1.17
    FY
    1.12
     CY
    1.12
     KL
    1.07
     cha
    1.06
     CJ
    0.99
    sta
    0.96
    Act Density 0.022%

    No Known Activations