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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or calls for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aker
    -0.17
    ilen
    -0.15
     èģ
    -0.15
    ÄĽj
    -0.15
    onga
    -0.15
    lte
    -0.14
    ante
    -0.14
    ual
    -0.13
    èĥİ
    -0.13
    è¼
    -0.13
    POSITIVE LOGITS
     kariy
    0.15
    quier
    0.14
    ologne
    0.14
    _AUX
    0.14
    opper
    0.14
    æ®
    0.14
    pcodes
    0.14
    رÛĮاÙĨ
    0.14
    FOUNDATION
    0.14
     benches
    0.14
    Act Density 0.951%

    No Known Activations