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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Posted" indicating the publication of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erer
    -0.17
    abay
    -0.16
    ides
    -0.16
    arch
    -0.16
    aaS
    -0.16
    953
    -0.15
    abal
    -0.15
    944
    -0.15
    oint
    -0.15
    lessly
    -0.14
    POSITIVE LOGITS
     bych
    0.18
     byste
    0.16
    ymm
    0.15
    å°¼äºļ
    0.15
    	on
    0.15
    ì§ĢìļĶ
    0.14
     gren
    0.14
     ADVISED
    0.14
     Bare
    0.14
    olute
    0.14
    Act Density 0.005%

    No Known Activations