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

    Neuronpedia

    INDEX
    Explanations

    scientific or scholarly research-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to investigation and inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zar
    -0.72
    perm
    -0.70
     Nadu
    -0.69
    corn
    -0.68
    adra
    -0.67
    cow
    -0.67
    Da
    -0.66
    lock
    -0.64
    Rated
    -0.63
    Gov
    -0.63
    POSITIVE LOGITS
    emouth
    0.88
    rador
    0.87
     Wond
    0.87
    ises
    0.82
    mingham
    0.76
     resear
    0.73
     eluc
    0.71
    idth
    0.70
    çīĪ
    0.68
    ostics
    0.68
    Act Density 0.038%

    No Known Activations