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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social justice and community support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ego
    -0.16
    ozo
    -0.15
    ampo
    -0.14
    еÑı
    -0.14
    adu
    -0.14
    ikal
    -0.14
     ticking
    -0.14
    ÑĤеÑĢи
    -0.14
    IndexChanged
    -0.13
    rias
    -0.13
    POSITIVE LOGITS
     eventually
    0.51
     Eventually
    0.48
    Eventually
    0.47
     eventual
    0.41
     ultimately
    0.32
     gradually
    0.27
    event
    0.27
     Ultimately
    0.25
     ultimate
    0.24
    Ultimately
    0.23
    Act Density 0.006%

    No Known Activations