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

    Neuronpedia

    INDEX
    Explanations

    references to comedic or humorous elements, particularly in relation to "punchlines."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usk
    -0.16
    income
    -0.15
    æ®Ĭ
    -0.14
    bero
    -0.14
    .cms
    -0.14
    mind
    -0.14
     Rub
    -0.14
    ollo
    -0.14
    engo
    -0.14
     rub
    -0.14
    POSITIVE LOGITS
     punch
    0.26
    y
    0.24
     punching
    0.23
     Punch
    0.22
    eson
    0.21
     holes
    0.21
     punched
    0.21
    arella
    0.20
    er
    0.20
    -hole
    0.20
    Act Density 0.009%

    No Known Activations