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

    Neuronpedia

    INDEX
    Explanations

    instances of specific names and references related to cultural or historical subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     erotiske
    -0.16
    Ñij
    -0.16
    era
    -0.16
    lings
    -0.15
     Ãł
    -0.15
    äng
    -0.15
    angen
    -0.15
    soever
    -0.15
     geschichten
    -0.15
    led
    -0.15
    POSITIVE LOGITS
     sz
    0.24
     egy
    0.24
    agy
    0.21
     Sz
    0.21
     harm
    0.20
     gy
    0.20
     legs
    0.20
     szer
    0.19
     ny
    0.19
    sz
    0.18
    Act Density 0.011%

    No Known Activations