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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the human body, specifically the neck

    oai_token-act-pair · gpt-3.5-turbo

    references to the neck

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ========
    -0.72
    ×ķ
    -0.70
    ordinary
    -0.67
    venants
    -0.67
    PLIED
    -0.67
    urity
    -0.65
    ISE
    -0.63
    anqu
    -0.61
    RED
    -0.60
    iesta
    -0.60
    POSITIVE LOGITS
    lace
    1.43
    tie
    1.27
    beard
    1.26
    lines
    1.14
    bones
    1.09
    line
    1.06
    bone
    1.03
    guards
    0.92
     neck
    0.90
    breaker
    0.87
    Act Density 0.009%

    No Known Activations