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

    Neuronpedia

    INDEX
    Explanations

    common actions and attributes of a person

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "he has" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.77
    mitting
    -0.70
    Eh
    -0.65
     Sass
    -0.64
    Gender
    -0.63
     Decoder
    -0.63
     Abuse
    -0.62
    ostic
    -0.62
    hee
    -0.62
    gee
    -0.60
    POSITIVE LOGITS
     himself
    0.80
     personally
    0.73
    liest
    0.70
    pocket
    0.67
     subordinates
    0.67
     quart
    0.67
     succeeded
    0.66
    ÃĥÃĤ
    0.66
     sued
    0.66
     flanked
    0.64
    Act Density 0.395%

    No Known Activations