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

    Neuronpedia

    INDEX
    Explanations

    phrases related to distance, specifically referring to proximity

    oai_token-act-pair · gpt-3.5-turbo

    instances of distance or proximity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conn
    -0.73
    oly
    -0.72
    nce
    -0.71
     streng
    -0.71
    cess
    -0.66
    iser
    -0.64
    Ku
    -0.64
    umn
    -0.63
    may
    -0.63
     mismatch
    -0.63
    POSITIVE LOGITS
    ruck
    0.79
    lier
    0.74
    sighted
    0.67
    seeing
    0.66
    aneously
    0.65
     Territories
    0.63
    Registered
    0.62
     away
    0.62
    fitted
    0.62
    heid
    0.61
    Act Density 0.023%

    No Known Activations