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

    Neuronpedia

    INDEX
    Explanations

    the name "Cand" followed by various suffixes or words

    oai_token-act-pair · gpt-3.5-turbo

    references to candidates or potential nominees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.94
    HF
    -0.71
    FactoryReloaded
    -0.70
     pity
    -0.68
     centrif
    -0.64
    FG
    -0.63
     DRAG
    -0.63
    STD
    -0.62
     Skydragon
    -0.61
    ORGE
    -0.61
    POSITIVE LOGITS
    idates
    1.38
    idate
    1.25
    lest
    1.20
    les
    1.01
    reon
    0.90
    encies
    0.90
    ulum
    0.89
    ida
    0.89
    arette
    0.89
    illo
    0.88
    Act Density 0.022%

    No Known Activations