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

    Neuronpedia

    INDEX
    Explanations

    terms related to the human spine

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the spine and vertebral structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mess
    -0.73
    miss
    -0.67
    ments
    -0.67
    ment
    -0.67
     Miss
    -0.66
    gat
    -0.66
    FA
    -0.63
     Ans
    -0.62
    mer
    -0.62
     Loans
    -0.60
    POSITIVE LOGITS
     spine
    4.00
     spinal
    1.73
     backbone
    1.67
     verte
    1.32
     torso
    1.16
     skull
    1.11
     guts
    1.10
     scalp
    1.09
     neck
    1.07
     nerve
    1.07
    Act Density 0.012%

    No Known Activations