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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating subtle suggestions or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Humph
    -0.15
    ptron
    -0.15
    atar
    -0.15
    ackers
    -0.15
    asper
    -0.15
    ìĸ¼
    -0.14
    iales
    -0.14
    egin
    -0.14
    inox
    -0.14
    retweeted
    -0.14
    POSITIVE LOGITS
    nings
    0.16
    inds
    0.15
     inn
    0.15
     ph
    0.14
     dawn
    0.14
     Knowledge
    0.14
    iana
    0.14
     Hogan
    0.14
     knowledge
    0.14
     Lifetime
    0.14
    Act Density 0.172%

    No Known Activations