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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, likely related to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "has."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interested
    -0.76
    seless
    -0.66
     Researchers
    -0.65
    winner
    -0.63
    OOL
    -0.62
     selves
    -0.60
     Recap
    -0.59
     Adults
    -0.57
     Measure
    -0.57
     IMAGES
    -0.57
    POSITIVE LOGITS
     been
    1.37
     vowed
    1.16
     apologized
    1.14
     campaigned
    1.14
     resigned
    1.12
    enegger
    1.11
     undergone
    1.10
    been
    1.09
     spoken
    1.08
     insisted
    1.08
    Act Density 0.225%

    No Known Activations