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

    Neuronpedia

    INDEX
    Explanations

    words related to leadership positions or hierarchies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competitive matchups and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ria
    -0.68
    Deploy
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
    Ö¼
    -0.63
    é¾
    -0.62
    åº
    -0.61
    TEXTURE
    -0.61
    ãĤ¢ãĥ«
    -0.60
    igue
    -0.60
     Cumm
    -0.59
    POSITIVE LOGITS
     Winston
    0.69
    ggle
    0.66
    sed
    0.64
    ĸļ
    0.64
    ikuman
    0.63
    pex
    0.63
    ivist
    0.62
     Gork
    0.61
     negotiator
    0.60
     scissors
    0.57
    Act Density 0.103%

    No Known Activations