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

    Neuronpedia

    INDEX
    Explanations

    phrases related to direction or location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "or"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTAL
    -0.67
    SPA
    -0.63
    encers
    -0.61
    eenth
    -0.60
    Ĥª
    -0.60
    SPONSORED
    -0.59
    scl
    -0.59
    ELS
    -0.58
     VIDEOS
    -0.58
    Sus
    -0.56
    POSITIVE LOGITS
    ific
    1.14
    izons
    1.12
    chid
    1.10
    ussia
    1.06
    acle
    1.04
    thodox
    0.97
    leans
    0.96
    ikawa
    0.95
    bid
    0.95
    lando
    0.95
    Act Density 0.043%

    No Known Activations