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

    Neuronpedia

    INDEX
    Explanations

    mentions of a size or condition that is smaller than normal or expected

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iership
    -0.73
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.69
    rite
    -0.68
    chwitz
    -0.67
    ICS
    -0.64
    lation
    -0.64
    igslist
    -0.60
     Topic
    -0.58
    midt
    -0.58
    idents
    -0.58
    POSITIVE LOGITS
    finger
    0.86
     girls
    0.81
    pox
    0.80
     boys
    0.79
     snippets
    0.77
     girl
    0.77
     boy
    0.76
     bit
    0.76
    bits
    0.75
     brother
    0.75
    Act Density 0.025%

    No Known Activations