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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals' names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isions
    -0.67
    itals
    -0.67
    lust
    -0.66
     prog
    -0.64
    sung
    -0.63
    heimer
    -0.63
     Instruments
    -0.62
    locks
    -0.62
    fell
    -0.62
    iate
    -0.61
    POSITIVE LOGITS
    lication
    0.85
    igree
    0.82
    ogly
    0.81
    ocene
    0.75
    olin
    0.74
    atri
    0.73
    ele
    0.72
    lli
    0.70
    alty
    0.70
    ocy
    0.69
    Act Density 0.098%

    No Known Activations