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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "message" and related expressions that convey significance or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĹ
    -0.15
    iske
    -0.15
    lero
    -0.15
    isen
    -0.14
    -pill
    -0.14
    ViewState
    -0.14
    乡
    -0.14
    LP
    -0.14
    ertos
    -0.14
    shire
    -0.14
    POSITIVE LOGITS
    immel
    0.16
    erah
    0.15
    esson
    0.15
    yntax
    0.15
    ylene
    0.14
     Rosen
    0.14
    urum
    0.13
    Cole
    0.13
     Benz
    0.13
    raphics
    0.13
    Act Density 0.026%

    No Known Activations