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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of mentioning or discussing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kool
    -0.53
     alá
    -0.53
     luto
    -0.51
     IActionResult
    -0.51
     Jol
    -0.50
     slutt
    -0.49
     Kamil
    -0.48
    thique
    -0.48
    UEGO
    -0.48
    Wal
    -0.48
    POSITIVE LOGITS
     mention
    1.35
     Mention
    1.35
     mentions
    1.34
     Mentions
    1.31
     Mentioned
    1.26
    Mention
    1.26
     mentioned
    1.24
     mentioning
    1.23
    mention
    1.21
    mentions
    1.07
    Act Density 0.179%

    No Known Activations