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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations and people

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and locations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Versions
    -0.68
    RO
    -0.67
    ione
    -0.64
    ories
    -0.64
    erate
    -0.62
    flags
    -0.62
    OLD
    -0.62
    ecided
    -0.62
    process
    -0.61
     addicts
    -0.61
    POSITIVE LOGITS
     whom
    0.95
    */(
    0.78
     Symphony
    0.68
     Jr
    0.66
    etime
    0.65
    pired
    0.61
     his
    0.60
     Tens
    0.59
     Celebrity
    0.59
     behalf
    0.58
    Act Density 0.209%

    No Known Activations