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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression and improvements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "along" or "those"

    np_acts-logits-general · gemini-2.0-flash

    along the lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.93
    SharedDtor
    -0.84
     myſelf
    -0.81
     themſelves
    -0.80
     مشارکت‌کنندگان
    -0.77
    Geplaatst
    -0.75
     INTERESAR
    -0.73
    __":
    -0.73
    Демографія
    -0.73
    PyExc
    -0.72
    POSITIVE LOGITS
     these
    0.70
    these
    0.57
    These
    0.55
     These
    0.54
    ские
    0.52
     plans
    0.50
    Cuáles
    0.50
    ные
    0.49
     свои
    0.48
    скими
    0.47
    Act Density 0.705%

    No Known Activations