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

    Neuronpedia

    INDEX
    Explanations

    throat-related words and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the throat and related actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udeb
    -0.71
     CES
    -0.64
    Amazon
    -0.63
     Athlet
    -0.63
    Haunted
    -0.61
    Avg
    -0.60
     Woodward
    -0.60
     Prosper
    -0.59
    atern
    -0.59
    ARC
    -0.59
    POSITIVE LOGITS
     throat
    1.29
     throats
    1.14
    pipe
    1.00
    bone
    1.00
     slit
    0.93
     cavity
    0.91
    piece
    0.89
    ħĭ
    0.89
    bones
    0.83
     lips
    0.82
    Act Density 0.005%

    No Known Activations