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

    Neuronpedia

    INDEX
    Explanations

    references to exclusions and limitations in a privacy or service context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilden
    -0.18
    .constructor
    -0.17
    rens
    -0.15
    ools
    -0.15
    ronic
    -0.15
     even
    -0.14
    éģ
    -0.14
     tern
    -0.14
    meden
    -0.14
     Even
    -0.14
    POSITIVE LOGITS
     nor
    0.19
    unless
    0.17
     unless
    0.16
     ucwords
    0.15
    oyer
    0.15
     Nor
    0.15
    izzato
    0.14
     anymore
    0.14
    pedia
    0.14
     neither
    0.14
    Act Density 0.116%

    No Known Activations