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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up" and variations of similar-sounding words or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eroon
    -0.16
    ermann
    -0.15
    mie
    -0.15
    atel
    -0.14
    nowled
    -0.14
    uda
    -0.14
    istics
    -0.14
    isan
    -0.14
    .ul
    -0.13
    важа
    -0.13
    POSITIVE LOGITS
    ieu
    0.17
    ublik
    0.16
    590
    0.15
    hti
    0.15
    	INNER
    0.14
     Managing
    0.14
    eu
    0.14
    arend
    0.14
    uestas
    0.14
    337
    0.14
    Act Density 0.056%

    No Known Activations