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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations or anticipated outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .LayoutStyle
    -0.16
    .addHandler
    -0.16
    çĹħ
    -0.15
    ëĭĪìķĦ
    -0.15
    (OS
    -0.14
     Ped
    -0.14
    croft
    -0.14
    .toolbox
    -0.14
    AQ
    -0.14
    chooser
    -0.14
    POSITIVE LOGITS
    ibble
    0.15
    лÑİ
    0.15
    uÃŃ
    0.15
    leme
    0.15
    otre
    0.14
    ziej
    0.14
    Äĩi
    0.14
     abstraction
    0.14
    uma
    0.13
    Bo
    0.13
    Act Density 0.242%

    No Known Activations