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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical movement and spatial location

    oai_token-act-pair · gpt-3.5-turbo

    actions related to movement or physical activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     historically
    -0.56
     ancest
    -0.56
     refere
    -0.52
     ancestry
    -0.52
    usalem
    -0.51
    ?).
    -0.49
     demonstr
    -0.49
    anium
    -0.49
    idas
    -0.48
     Represent
    -0.48
    POSITIVE LOGITS
     again
    0.78
    again
    0.74
    ADRA
    0.68
    byss
    0.60
    MSN
    0.59
    ij士
    0.59
    Conclusion
    0.58
    Again
    0.58
     Again
    0.58
    raq
    0.57
    Act Density 1.172%

    No Known Activations