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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    collective statements or references to a group or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peak
    -0.75
     Nin
    -0.67
     Lup
    -0.66
     Hok
    -0.65
     Leaf
    -0.64
     Outside
    -0.63
     Chapters
    -0.62
     Bates
    -0.60
     Bout
    -0.60
     Blackwell
    -0.59
    POSITIVE LOGITS
    etheless
    0.95
    cause
    0.85
    NetMessage
    0.82
    chwitz
    0.81
    merce
    0.79
    MpServer
    0.79
    issance
    0.78
    bsp
    0.76
     sugg
    0.76
    ernels
    0.75
    Act Density 0.649%

    No Known Activations