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

    Neuronpedia

    INDEX
    Explanations

    names that start with the letter "L"

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals and their associated actions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĤ¯
    -0.68
     INT
    -0.67
    ndra
    -0.66
    ulative
    -0.66
    heric
    -0.62
    oulos
    -0.62
     cour
    -0.62
    idious
    -0.61
    venient
    -0.61
    worldly
    -0.60
    POSITIVE LOGITS
    allows
    0.69
     drawer
    0.66
    Chance
    0.65
     Downing
    0.65
    çĶŁ
    0.64
    jong
    0.63
    horn
    0.63
    bats
    0.61
    gov
    0.60
    CHAT
    0.60
    Act Density 0.308%

    No Known Activations