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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that emphasize connection and addition

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

    Followed by a determiner ("a", "an")

    np_acts-logits-general · gemini-2.0-flash

    adding and or but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.89
     poveznice
    -0.78
     '\\;'
    -0.76
    rrggbb
    -0.72
    AndEndTag
    -0.70
    تقاوى
    -0.69
    reportWebVitals
    -0.68
    IUrlHelper
    -0.68
    styleType
    -0.68
     octaves
    -0.68
    POSITIVE LOGITS
     a
    0.96
     an
    0.94
     plenty
    0.82
     lots
    0.81
     no
    0.67
     strong
    0.63
    SequentialGroup
    0.60
     some
    0.59
     great
    0.59
     Lots
    0.57
    Act Density 0.480%

    No Known Activations