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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that evaluate or contrast different subjects

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

    more than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.38
     beginnetje
    -0.37
     tro
    -0.35
     ch
    -0.34
     solo
    -0.33
    RenderAtEndOf
    -0.33
    ofire
    -0.32
     Сере
    -0.31
     Mole
    -0.30
    solo
    -0.30
    POSITIVE LOGITS
     pouvoit
    0.61
    ="@+
    0.58
    Worse
    0.56
    ⟬
    0.56
     feroit
    0.54
     étoient
    0.53
     kasarigan
    0.53
     étoit
    0.52
    PyExc
    0.52
     auroit
    0.52
    Act Density 0.141%

    No Known Activations