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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "con."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èŃľ
    -0.18
    -vous
    -0.16
    urgy
    -0.15
    ÅĽcie
    -0.15
    shake
    -0.15
    544
    -0.14
    berman
    -0.14
    UDA
    -0.14
    aukee
    -0.14
    heets
    -0.14
    POSITIVE LOGITS
    aire
    0.18
    yš
    0.16
    ito
    0.16
     Spor
    0.16
    -collapse
    0.15
    (equalTo
    0.15
    ìŀħ
    0.15
    yb
    0.14
    sWith
    0.14
    ãĤ¿ãĥ³
    0.14
    Act Density 0.041%

    No Known Activations