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

    Neuronpedia

    INDEX
    Explanations

    phrases that signify strong performance metrics or leadership qualities in individuals

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

    Preceding word is followed by "has"

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by has

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    newswire
    -0.57
     Wiktionnaire
    -0.54
    EDEFAULT
    -0.51
    /**
    -0.47
    later
    -0.46
    XmlSchema
    -0.46
    zumaki
    -0.46
    ThroughAttribute
    -0.45
    ambilan
    -0.45
    orrow
    -0.45
    POSITIVE LOGITS
     has
    1.90
     telah
    1.63
     have
    1.50
    has
    1.44
     đã
    1.41
    Has
    1.40
     hasn
    1.36
     hath
    1.31
     Has
    1.22
     heeft
    1.16
    Act Density 0.597%

    No Known Activations