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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "after."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ags
    -0.15
    hec
    -0.15
    eam
    -0.14
     Trophy
    -0.14
    anten
    -0.14
    ìĥģ
    -0.14
    riangle
    -0.14
    òn
    -0.13
    nez
    -0.13
    asing
    -0.13
    POSITIVE LOGITS
     being
    0.21
     previously
    0.15
    481
    0.15
    tom
    0.15
     recent
    0.15
     footage
    0.15
     having
    0.14
     three
    0.14
     earlier
    0.14
    299
    0.14
    Act Density 0.053%

    No Known Activations