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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating academic institutions and educational qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yard
    -0.15
     noc
    -0.15
    avs
    -0.14
    .dm
    -0.14
     twe
    -0.13
    æ±ĩ
    -0.13
     заклад
    -0.13
    verty
    -0.13
    awy
    -0.13
    anje
    -0.13
    POSITIVE LOGITS
    ologie
    0.20
     Fors
    0.20
     Polit
    0.19
     Eth
    0.17
     So
    0.17
    Polit
    0.17
     Belle
    0.17
     pad
    0.17
     Liter
    0.17
     Arch
    0.16
    Act Density 0.046%

    No Known Activations