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

    Neuronpedia

    INDEX
    Explanations

    words related to the human body

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bodily structures and waste

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.98
    xual
    -0.96
    hips
    -0.90
    es
    -0.90
    ournal
    -0.81
    ¶æ
    -0.80
    e
    -0.79
    hip
    -0.76
    CI
    -0.75
    yne
    -0.75
    POSITIVE LOGITS
    brance
    0.77
    Ship
    0.75
    awar
    0.74
    urbed
    0.72
    ressed
    0.70
    butt
    0.70
    iless
    0.70
    urb
    0.70
    ger
    0.70
    ancing
    0.69
    Act Density 0.121%

    No Known Activations