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

    Neuronpedia

    INDEX
    Explanations

    dates or events in political context

    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
    place
    -0.73
    ãĤ©
    -0.70
    inctions
    -0.65
    pter
    -0.65
    inelli
    -0.65
    dayName
    -0.63
    utch
    -0.61
    strings
    -0.61
     Dolphin
    -0.60
    users
    -0.58
    POSITIVE LOGITS
    IENT
    1.18
    OR
    1.10
    GAN
    1.07
    IES
    1.04
    OGR
    0.97
    RY
    0.96
    IFIED
    0.96
    IZ
    0.95
    ATIVE
    0.94
    ourke
    0.93
    Act Density 0.010%

    No Known Activations