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

    Neuronpedia

    INDEX
    Explanations

    pronouns and phrases indicating involvement or agency in actions

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

    Sentences starting with "We"

    np_acts-logits-general · gemini-2.0-flash

    we + academic verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.87
    RectangleBorder
    -0.84
     שוליים
    -0.81
    InputBorder
    -0.79
     يتيمه
    -0.76
    kháu
    -0.74
    bootstrapcdn
    -0.73
    ]--;
    -0.72
    клопе
    -0.71
     AttributeSet
    -0.70
    POSITIVE LOGITS
     alſo
    0.65
     also
    0.62
    <bos>
    0.59
     continued
    0.58
     found
    0.57
     then
    0.55
     ſhould
    0.54
     will
    0.54
     would
    0.53
     muſt
    0.52
    Act Density 1.753%

    No Known Activations