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

    Neuronpedia

    INDEX
    Explanations

    phrases related to objectives or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellen
    -0.15
    -Line
    -0.14
    iki
    -0.14
    иÑĩеÑģкое
    -0.14
    apesh
    -0.14
    ä½ľ
    -0.14
    helm
    -0.14
    ãĥ©ãĤ¤ãĥ³
    -0.14
    mite
    -0.13
    cba
    -0.13
    POSITIVE LOGITS
    tes
    0.21
    plevel
    0.20
    asts
    0.20
    ying
    0.20
    oted
    0.18
    gether
    0.18
    ogle
    0.18
    obus
    0.17
     boot
    0.17
    iling
    0.17
    Act Density 0.247%

    No Known Activations