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

    Neuronpedia

    INDEX
    Explanations

    terms and patterns related to mocking in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĢοÏį
    -0.07
    wo
    -0.06
    arsi
    -0.06
    ÙijÙı
    -0.06
    fore
    -0.06
     Abrams
    -0.06
     Advent
    -0.06
    082
    -0.06
    ège
    -0.05
    gio
    -0.05
    POSITIVE LOGITS
    chwitz
    0.08
    ITO
    0.08
    ito
    0.08
    _PATCH
    0.08
     Patch
    0.08
    rak
    0.08
     patched
    0.08
    .Mock
    0.07
    Patch
    0.07
    loquent
    0.07
    Act Density 0.001%

    No Known Activations