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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yled
    -0.15
    iri
    -0.14
     Garage
    -0.14
     Swe
    -0.14
     alien
    -0.14
    anc
    -0.14
    immers
    -0.14
    Bed
    -0.13
     sais
    -0.13
    iris
    -0.13
    POSITIVE LOGITS
    oders
    0.17
    à¸ļาล
    0.14
    remen
    0.14
    DRV
    0.14
    PKG
    0.14
    andidate
    0.14
    enguin
    0.14
    imenti
    0.14
    loff
    0.14
     Dolphin
    0.13
    Act Density 0.003%

    No Known Activations