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

    Neuronpedia

    INDEX
    Explanations

    expressions related to contradictions and critiques of conditions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifdef
    -0.17
    ongan
    -0.16
    kv
    -0.14
    ÎŃνÏĦ
    -0.14
    ocz
    -0.14
    ToLocal
    -0.14
    okay
    -0.14
    ctic
    -0.14
    aj
    -0.13
    ledo
    -0.13
    POSITIVE LOGITS
    ips
    0.15
    ãģĸ
    0.15
    agram
    0.14
     charged
    0.14
    upal
    0.13
    ()(
    0.13
     ought
    0.13
     dissolved
    0.13
    ãĤ¸ãĤ¢
    0.13
    Charge
    0.13
    Act Density 0.137%

    No Known Activations