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

    Neuronpedia

    INDEX
    Explanations

    the abbreviation "lol" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of laughter or humor expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rament
    -0.79
     glim
    -0.77
     bounds
    -0.73
    éĹ
    -0.72
    ãĤ©
    -0.72
    ":["
    -0.69
    arnaev
    -0.65
    States
    -0.64
    legates
    -0.64
     contracted
    -0.64
    POSITIVE LOGITS
    ipop
    1.37
    ita
    1.17
    cow
    1.05
    cats
    1.01
    ogie
    0.84
    zers
    0.81
    ibaba
    0.78
    hattan
    0.77
    creen
    0.77
    ogy
    0.73
    Act Density 0.028%

    No Known Activations