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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ve" as a contraction for "have."

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

    instances of the verb "have" in various forms

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

    I've followed by past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.56
    AccessorTable
    -0.55
    Pozdrawiam
    -0.53
     toto
    -0.52
     a
    -0.50
    reaction
    -0.49
    ponses
    -0.49
    bgp
    -0.48
    the
    -0.47
     hemma
    -0.47
    POSITIVE LOGITS
     got
    0.84
     already
    0.83
     been
    0.82
    tvguidetime
    0.82
     gotta
    0.82
     always
    0.81
     never
    0.73
    ParallelGroup
    0.69
    InstanceState
    0.65
    IGraphics
    0.65
    Act Density 0.027%

    No Known Activations