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

    Neuronpedia

    INDEX
    Explanations

    mentions of clothing or uniforms worn by individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     intrins
    -0.72
     selves
    -0.70
     cities
    -0.70
     settlements
    -0.68
     affiliates
    -0.68
     members
    -0.67
    yond
    -0.66
    theless
    -0.65
     allowable
    -0.64
    erness
    -0.64
    POSITIVE LOGITS
     whom
    0.81
    otto
    0.72
     ape
    0.67
     stole
    0.67
    chief
    0.66
    ãĤ¨ãĥ«
    0.65
    ãĥĺ
    0.65
     gorilla
    0.65
     throne
    0.64
     sunglasses
    0.63
    Act Density 0.297%

    No Known Activations