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

    Neuronpedia

    INDEX
    Explanations

    proper names, particularly those associated with individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onda
    -0.17
    uju
    -0.15
    formats
    -0.15
     kims
    -0.14
    utto
    -0.14
    uky
    -0.14
     (;;)
    -0.14
    uja
    -0.14
    etc
    -0.14
    cie
    -0.14
    POSITIVE LOGITS
     captain
    0.23
     yellow
    0.22
     capt
    0.20
    _yellow
    0.19
    Yellow
    0.19
     substitute
    0.19
     Unused
    0.19
     Yellow
    0.19
    undle
    0.19
     captains
    0.19
    Act Density 0.017%

    No Known Activations