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

    Neuronpedia

    INDEX
    Explanations

    phrases where two entities or objects are presented in close proximity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "side by side."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AH
    -0.83
     TAMADRA
    -0.70
    Bey
    -0.68
    Haw
    -0.66
     Bees
    -0.63
     avail
    -0.62
     Bee
    -0.61
    AGES
    -0.61
    pell
    -0.61
     Beacon
    -0.60
    POSITIVE LOGITS
     Side
    1.08
     side
    1.05
    side
    0.98
    Side
    0.93
     sidebar
    0.81
    slice
    0.78
    iera
    0.76
    sid
    0.76
    ward
    0.71
    reverse
    0.71
    Act Density 0.019%

    No Known Activations