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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical symbols and formatting elements in equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akan
    -0.19
    zel
    -0.17
     Stra
    -0.15
    ingen
    -0.14
    uard
    -0.13
    ä»ķ
    -0.13
    Stra
    -0.13
    enek
    -0.13
    nore
    -0.13
    ider
    -0.13
    POSITIVE LOGITS
    ëłµ
    0.17
    ADDE
    0.15
    kke
    0.14
    _INCREMENT
    0.14
    à¤Ł
    0.14
    cretion
    0.14
    ον
    0.13
    ipeg
    0.13
    .asp
    0.13
    ượng
    0.13
    Act Density 0.002%

    No Known Activations