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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences explaining reasons or justifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing knowledge or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xit
    -0.83
    isode
    -0.73
    lez
    -0.72
    anon
    -0.71
     âĵĺ
    -0.71
    ESA
    -0.70
     Appears
    -0.70
    jri
    -0.69
    udos
    -0.68
    âĢİ
    -0.67
    POSITIVE LOGITS
     outnumbered
    0.78
     pree
    0.73
     messed
    0.71
     collateral
    0.71
     %%
    0.70
     outwe
    0.69
     cheap
    0.68
     technically
    0.67
     verte
    0.66
     scarce
    0.65
    Act Density 0.580%

    No Known Activations