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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases related to personal attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    elements related to personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assies
    -0.68
    LAN
    -0.67
    mpeg
    -0.66
    slave
    -0.65
    Ranked
    -0.63
    chief
    -0.62
    é¾į
    -0.62
    Gs
    -0.61
    onds
    -0.61
    Adv
    -0.61
    POSITIVE LOGITS
     minded
    1.20
    isable
    1.18
    istic
    1.17
    istically
    1.07
    ized
    1.01
    izable
    0.98
     sounding
    0.94
    worldly
    0.93
    ised
    0.91
    idious
    0.91
    Act Density 0.285%

    No Known Activations