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

    Neuronpedia

    INDEX
    Explanations

    key terms related to choices and decisions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihat
    -0.15
    indow
    -0.15
    ãĥ¼ãĥĵãĤ¹
    -0.15
    astle
    -0.14
    extView
    -0.14
    BAR
    -0.14
    ãĥ¼ãĥĵ
    -0.13
    _fds
    -0.13
    zcze
    -0.13
    ible
    -0.13
    POSITIVE LOGITS
     Flake
    0.15
    ulong
    0.15
    inker
    0.15
    bul
    0.14
     Marsh
    0.14
    ereco
    0.14
    onders
    0.14
     demands
    0.14
     ho
    0.14
     bul
    0.14
    Act Density 0.001%

    No Known Activations