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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a query or a question

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leftright
    -0.16
    ourmet
    -0.16
     luc
    -0.16
    ãĥ¼ãĥĵ
    -0.15
    ierung
    -0.15
    CPP
    -0.14
    itional
    -0.14
    AndPassword
    -0.13
    407
    -0.13
    kas
    -0.13
    POSITIVE LOGITS
    ODO
    0.17
    ards
    0.16
    fts
    0.15
    iner
    0.15
    yun
    0.14
    ãĤ¤ãĥī
    0.14
    odable
    0.14
    éli
    0.14
    VERTISEMENT
    0.14
    iid
    0.14
    Act Density 0.015%

    No Known Activations