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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "once" and similar temporal phrases that indicate a sequence of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kiem
    -0.15
    ãģŁãģĹ
    -0.14
    buch
    -0.14
    åĨµ
    -0.14
    ertino
    -0.14
    isel
    -0.14
    кÑĥÑĤ
    -0.14
    меÑī
    -0.14
    .Gravity
    -0.13
    arp
    -0.13
    POSITIVE LOGITS
     xong
    0.18
    azard
    0.15
    aign
    0.15
    tero
    0.14
    words
    0.14
    OwnProperty
    0.14
     finishes
    0.14
    879
    0.14
    å®ĮæĪIJ
    0.14
     viá»ĩn
    0.14
    Act Density 0.076%

    No Known Activations