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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate audience engagement or performance evaluation concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Card
    -0.15
    ÑĦоÑĢми
    -0.15
    üssen
    -0.13
    catid
    -0.13
    CharCode
    -0.13
    оÑĥ
    -0.13
    ìļ±
    -0.13
    cap
    -0.13
    .mj
    -0.13
    acey
    -0.13
    POSITIVE LOGITS
     c
    0.26
    _c
    0.24
    _C
    0.23
     C
    0.23
    -c
    0.23
    Âłc
    0.21
    .c
    0.21
    C
    0.21
    ÂłC
    0.21
    	c
    0.20
    Act Density 0.356%

    No Known Activations