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

    Neuronpedia

    INDEX
    Explanations

    passages related to political statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to notable figures and their actions or legacies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TOD
    -0.47
    —-
    -0.44
    eph
    -0.43
     Potion
    -0.43
     Distance
    -0.43
     LH
    -0.42
    Beta
    -0.42
     Horizon
    -0.42
     Instrument
    -0.42
    FS
    -0.41
    POSITIVE LOGITS
    etheless
    0.97
     hereby
    0.76
     nevertheless
    0.64
     nonetheless
    0.64
    utterstock
    0.57
    ASHINGTON
    0.57
     respectively
    0.57
    geries
    0.57
     attest
    0.56
    tis
    0.55
    Act Density 0.699%

    No Known Activations