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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "rot"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "rotation" or "rotating."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nect
    -0.81
     EntityItem
    -0.77
    omething
    -0.70
     TOTAL
    -0.69
     Mellon
    -0.65
     charism
    -0.64
    ynthesis
    -0.62
    inez
    -0.61
     Asians
    -0.61
    erry
    -0.61
    POSITIVE LOGITS
    ations
    1.11
    unda
    1.10
    ational
    1.08
    ife
    0.89
    ional
    0.87
    oscope
    0.85
    atory
    0.82
    ary
    0.79
    atile
    0.79
    ievers
    0.78
    Act Density 0.032%

    No Known Activations