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

    Neuronpedia

    INDEX
    Explanations

    names of places and specific geographical or cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omb
    -0.15
    izations
    -0.14
    avery
    -0.14
    abus
    -0.14
    umu
    -0.14
    /the
    -0.13
    士
    -0.13
    eyin
    -0.13
    éré
    -0.13
     Feder
    -0.13
    POSITIVE LOGITS
    éĽĨä¸Ń
    0.15
     forgiven
    0.14
    ÙĬØ«
    0.14
    飯
    0.14
    /releases
    0.14
    /on
    0.14
    iÄį
    0.14
    erif
    0.14
    qual
    0.14
    radient
    0.13
    Act Density 0.453%

    No Known Activations