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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific range or type of something

    oai_token-act-pair · gpt-3.5-turbo

    references to various "spectrum" concepts across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiro
    -0.79
    lisher
    -0.67
    bear
    -0.65
    lishes
    -0.64
    ished
    -0.64
    BY
    -0.63
    than
    -0.62
    ishable
    -0.62
    ears
    -0.61
    inse
    -0.61
    POSITIVE LOGITS
     spectrum
    1.17
     Spectrum
    0.99
    geist
    0.91
    atile
    0.80
    anches
    0.75
    daq
    0.72
    atility
    0.71
    ittal
    0.70
     holdings
    0.69
    schild
    0.69
    Act Density 0.007%

    No Known Activations