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

    Neuronpedia

    INDEX
    Explanations

    sentences describing tasks or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the process of achievement or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.76
     plates
    -0.66
    izens
    -0.65
    umbs
    -0.62
    bats
    -0.62
    sburg
    -0.62
    chev
    -0.61
     Nig
    -0.60
    bies
    -0.60
     personalities
    -0.58
    POSITIVE LOGITS
     contrasted
    0.95
     borne
    0.91
     certainly
    0.85
     also
    0.83
     understandable
    0.79
     analogous
    0.78
     essentially
    0.78
     undoubtedly
    0.77
     especially
    0.77
     likely
    0.76
    Act Density 0.189%

    No Known Activations