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

    Neuronpedia

    INDEX
    Explanations

    references to political events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oders
    -0.16
    ÑĪÑĤ
    -0.16
    ÃŃž
    -0.15
    ubat
    -0.14
    ippo
    -0.14
    omap
    -0.14
    άÏģ
    -0.14
    ught
    -0.14
    ntl
    -0.14
    yles
    -0.14
    POSITIVE LOGITS
     Punch
    0.24
     Vanguard
    0.19
    chwitz
    0.18
     punch
    0.17
     Sunday
    0.17
     Sahara
    0.17
     NAN
    0.16
    lear
    0.15
    inÄĽ
    0.15
    anguard
    0.15
    Act Density 0.031%

    No Known Activations