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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical rotation or cycling

    oai_token-act-pair · gpt-3.5-turbo

    references to rotational dynamics or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stract
    -0.75
    asper
    -0.74
    tein
    -0.70
     Pyr
    -0.68
    ramid
    -0.68
    CHA
    -0.66
    adr
    -0.66
    Priv
    -0.65
    Obama
    -0.65
     Asians
    -0.65
    POSITIVE LOGITS
     rotation
    1.20
     destro
    0.88
     rotate
    0.83
     rotated
    0.81
     rotating
    0.74
     sickness
    0.74
     purge
    0.73
     revolves
    0.73
    iferation
    0.73
    ĸļ
    0.73
    Act Density 0.005%

    No Known Activations