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

    Neuronpedia

    INDEX
    Explanations

    words related to the spine and vertebral column

    oai_token-act-pair · gpt-3.5-turbo

    references to the spine or vertebrae

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arettes
    -0.72
    opol
    -0.72
    icable
    -0.70
    ilities
    -0.68
     AP
    -0.67
    icably
    -0.67
    ITNESS
    -0.67
    egu
    -0.66
    ogl
    -0.65
    eanor
    -0.64
    POSITIVE LOGITS
     spine
    1.35
     marrow
    1.04
    bone
    0.95
    bones
    0.89
     verte
    0.84
     necks
    0.83
     veins
    0.81
     craw
    0.81
    tie
    0.80
    side
    0.79
    Act Density 0.005%

    No Known Activations