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

    Neuronpedia

    INDEX
    Explanations

    instances of humor and puns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĵãĤĵãģ«
    -0.15
    caps
    -0.15
    inoa
    -0.14
     Slov
    -0.14
    avra
    -0.14
    usercontent
    -0.14
    :UIAlert
    -0.13
    unce
    -0.13
    oute
    -0.13
    ÅĽci
    -0.13
    POSITIVE LOGITS
    ulp
    0.17
    kins
    0.16
    rung
    0.15
     Chaos
    0.15
    omet
    0.15
    elps
    0.15
    fraction
    0.14
    igers
    0.14
    iyi
    0.14
    erals
    0.14
    Act Density 0.007%

    No Known Activations