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

    Neuronpedia

    INDEX
    Explanations

    instances of people being impacted or affected by various situations or issues

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alyst
    -0.67
     Recap
    -0.67
    ISS
    -0.67
    onement
    -0.66
    umping
    -0.66
    ablishment
    -0.64
    ür
    -0.62
    forcement
    -0.61
    iss
    -0.60
    ERAL
    -0.60
    POSITIVE LOGITS
     undergone
    1.27
     benefited
    1.27
     been
    1.25
     suffered
    1.18
     gotten
    1.17
     migrated
    1.15
     lived
    1.12
    been
    1.11
     endured
    1.11
     participated
    1.09
    Act Density 0.162%

    No Known Activations