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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "have" to indicate possession or occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grew
    -0.92
    Saw
    -0.90
     Saw
    -0.90
    wrote
    -0.89
    saw
    -0.86
     saw
    -0.81
    knew
    -0.80
     Took
    -0.77
     Gave
    -0.76
    threw
    -0.74
    POSITIVE LOGITS
     been
    1.63
     gone
    1.54
     gotten
    1.48
     taken
    1.40
     fallen
    1.29
     done
    1.25
     risen
    1.22
     shown
    1.19
     begun
    1.18
     undergone
    1.16
    Act Density 0.469%

    No Known Activations