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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to a wide range or variety of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of spectrum, particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiro
    -0.77
    than
    -0.71
    ished
    -0.66
    ears
    -0.63
     Oblivion
    -0.62
    bear
    -0.61
    ever
    -0.61
    verbs
    -0.61
    orc
    -0.60
    lymp
    -0.60
    POSITIVE LOGITS
     spectrum
    1.14
     Spectrum
    1.02
    geist
    0.84
    atile
    0.76
     analy
    0.74
    naire
    0.71
    anches
    0.70
    atility
    0.69
     allocation
    0.69
     allocations
    0.68
    Act Density 0.008%

    No Known Activations