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

    Neuronpedia

    INDEX
    Explanations

    mentions of or references to foreigners

    oai_token-act-pair · gpt-3.5-turbo

    references to foreigners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucc
    -0.69
     submission
    -0.65
    aughters
    -0.64
    ady
    -0.64
     Parenthood
    -0.63
    arah
    -0.62
    Development
    -0.62
    Ħ¢
    -0.62
    aton
    -0.62
    heny
    -0.62
    POSITIVE LOGITS
     alike
    1.02
     abroad
    0.91
     whom
    0.84
     who
    0.81
    ophone
    0.79
     poured
    0.77
    ourced
    0.76
     pouring
    0.75
     residing
    0.74
    paces
    0.74
    Act Density 0.038%

    No Known Activations