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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "have"

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

    Following "has" or "have"

    np_acts-logits-general · gemini-2.0-flash

    has/have + past tense verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jefus
    -0.72
     /\.
    -0.71
     defStyle
    -0.68
     poffible
    -0.64
     Perſ
    -0.62
     provinciale
    -0.61
     ſche
    -0.61
     urbanos
    -0.61
     perfons
    -0.60
     marins
    -0.60
    POSITIVE LOGITS
     have
    0.96
     be
    0.94
    ')):
    0.82
    "):
    0.81
     also
    0.81
     hold
    0.75
     not
    0.72
    ')")
    0.72
    '):
    0.71
    "))
    0.71
    Act Density 0.247%

    No Known Activations