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

    Neuronpedia

    INDEX
    Explanations

    strong emotional or impactful words and phrases related to strong opinions or arguments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial metrics and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mos
    -0.73
    kus
    -0.69
    ©¶æ
    -0.69
    paren
    -0.65
    itans
    -0.63
    tions
    -0.63
    OTOS
    -0.63
     Niet
    -0.63
    amas
    -0.61
    arov
    -0.61
    POSITIVE LOGITS
    naire
    0.93
    naires
    0.87
    ously
    0.83
     ridden
    0.83
    ous
    0.82
    oused
    0.80
    iest
    0.78
    hower
    0.78
    eering
    0.76
    ishly
    0.75
    Act Density 0.175%

    No Known Activations