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

    Neuronpedia

    INDEX
    Explanations

    the word "have" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.72
    oshi
    -0.71
    icking
    -0.64
    weed
    -0.59
    patch
    -0.57
    TG
    -0.57
     Apart
    -0.57
    bies
    -0.56
    wait
    -0.55
     Byz
    -0.55
    POSITIVE LOGITS
     been
    1.28
    been
    1.16
     Been
    0.95
     gotten
    0.89
     undergone
    0.86
     become
    0.85
     seen
    0.84
     survived
    0.81
     done
    0.80
     no
    0.79
    Act Density 0.272%

    No Known Activations