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

    Neuronpedia

    INDEX
    Explanations

    medical instruments

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with a pendulum or swinging motion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Direct
    -0.63
     co
    -0.61
     Raw
    -0.58
     sadd
    -0.58
     st
    -0.58
     se
    -0.57
     raw
    -0.56
     OW
    -0.56
     Star
    -0.56
     Od
    -0.55
    POSITIVE LOGITS
    ulum
    4.93
    ula
    1.73
    ulo
    1.52
    uum
    1.28
    ulus
    1.27
    ulous
    1.25
    ulas
    1.22
    uli
    1.20
    ulin
    1.20
    ular
    1.19
    Act Density 0.011%

    No Known Activations