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

    Neuronpedia

    INDEX
    Explanations

    people or entities that have been supported or consulted or have shared certain characteristics or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "have" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arter
    -0.73
     Apart
    -0.68
    hand
    -0.68
    hatt
    -0.65
    OOL
    -0.60
     Admir
    -0.59
     Crown
    -0.58
     Recap
    -0.58
     Anyway
    -0.57
    ensing
    -0.56
    POSITIVE LOGITS
     been
    1.43
    been
    1.36
     undergone
    1.24
     arisen
    1.10
     endured
    1.07
     gotten
    1.03
     become
    1.01
     worked
    0.99
     survived
    0.97
     risen
    0.97
    Act Density 0.141%

    No Known Activations