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

    Neuronpedia

    INDEX
    Explanations

    pronouns and names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals speaking or being mentioned within the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Offline
    -0.64
    Higher
    -0.60
     Millennium
    -0.60
    Remove
    -0.59
    Measure
    -0.58
     Keeper
    -0.57
    ļéĨĴ
    -0.57
    assembly
    -0.57
     Hybrid
    -0.57
    iterator
    -0.57
    POSITIVE LOGITS
     nevertheless
    1.33
     nonetheless
    1.28
     certainly
    1.22
    'll
    1.20
     did
    1.15
     didn
    1.10
    'd
    1.09
    zbollah
    1.05
     surely
    1.05
     doubtless
    1.03
    Act Density 0.240%

    No Known Activations