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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to media, particularly films or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñij
    -0.17
    äng
    -0.15
    era
    -0.15
    angen
    -0.15
    idget
    -0.15
    lings
    -0.15
    //=
    -0.15
     kä
    -0.14
    ä
    -0.14
    soever
    -0.14
    POSITIVE LOGITS
     sz
    0.25
     egy
    0.23
    agy
    0.22
     gy
    0.21
     Sz
    0.21
     szer
    0.20
     cs
    0.20
     harm
    0.20
     Cs
    0.19
     legs
    0.19
    Act Density 0.017%

    No Known Activations