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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or notable moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spite
    -0.18
    ìŀIJìĿ¸
    -0.15
     retrospect
    -0.15
    roph
    -0.15
    ellation
    -0.15
    enan
    -0.14
    plevel
    -0.14
     hindsight
    -0.14
    irs
    -0.14
    tempts
    -0.13
    POSITIVE LOGITS
     addition
    0.32
     Addition
    0.26
     essence
    0.23
     additions
    0.23
     short
    0.21
     mere
    0.21
     add
    0.20
     doing
    0.20
     additional
    0.19
    -add
    0.19
    Act Density 0.077%

    No Known Activations