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

    Neuronpedia

    INDEX
    Explanations

    references to film titles or names of directors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.18
    ãĥªãĥ¼ãĤº
    -0.18
    ish
    -0.17
    ÄĽk
    -0.15
    htub
    -0.15
    ation
    -0.15
    Occurred
    -0.14
    statt
    -0.14
    ijing
    -0.14
    phalt
    -0.14
    POSITIVE LOGITS
    ors
    0.19
    tures
    0.16
    ëĭ¤
    0.16
    /umd
    0.15
    heads
    0.15
    borne
    0.14
    aidu
    0.14
    forth
    0.14
    ussen
    0.14
    hw
    0.14
    Act Density 0.049%

    No Known Activations