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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "once" in various contexts, indicating a focus on sequential or conditional actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isko
    -0.17
    ¢
    -0.16
    IColor
    -0.15
    ernet
    -0.14
    -0.14
    ibar
    -0.14
    ammed
    -0.14
    antine
    -0.14
    oki
    -0.13
    oui
    -0.13
    POSITIVE LOGITS
    erie
    0.16
    egra
    0.15
    ãģĿ
    0.15
    _registro
    0.14
    -forward
    0.14
    ture
    0.14
    _CB
    0.13
    /loose
    0.13
    rozen
    0.13
    575
    0.13
    Act Density 0.065%

    No Known Activations