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

    Neuronpedia

    INDEX
    Explanations

    pronouns or phrases referring to unknown identities or subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.64
    eme
    -0.64
    framework
    -0.63
     absence
    -0.62
    GV
    -0.60
    strip
    -0.60
     caution
    -0.59
    ranging
    -0.59
     saturation
    -0.58
    earchers
    -0.58
    POSITIVE LOGITS
     owns
    1.32
     else
    1.09
     cares
    1.03
     knows
    1.00
     pays
    0.98
     occupies
    0.98
    oping
    0.97
     participates
    0.95
     deserves
    0.93
     governs
    0.92
    Act Density 0.048%

    No Known Activations