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

    Neuronpedia

    INDEX
    Explanations

    equations and mathematical expressions related to theoretical constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æŃ¯
    -0.15
    æijĺ
    -0.14
    rollo
    -0.14
    adem
    -0.14
    cela
    -0.14
    etimes
    -0.14
    ÃĹ</
    -0.14
    izr
    -0.14
     ÑĢоб
    -0.14
    agon
    -0.14
    POSITIVE LOGITS
     note
    0.22
     Notice
    0.22
     Note
    0.22
     notice
    0.21
    Note
    0.20
    Notice
    0.19
     now
    0.19
     Now
    0.19
    since
    0.16
     noting
    0.16
    Act Density 0.156%

    No Known Activations