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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or the concept of "another" in relation to negative or unnecessary events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÂŃn
    -0.17
    Const
    -0.14
    -backed
    -0.14
    ogue
    -0.14
    nt
    -0.14
    imit
    -0.14
    ARAM
    -0.13
    lass
    -0.13
     Mature
    -0.13
     declar
    -0.13
    POSITIVE LOGITS
    addtogroup
    0.18
    tees
    0.18
    gow
    0.16
    anzi
    0.15
    inois
    0.15
    alars
    0.15
    urette
    0.15
    inder
    0.15
    elib
    0.15
    edla
    0.14
    Act Density 0.220%

    No Known Activations