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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recent realizations or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "just."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Proto
    -0.63
     Likely
    -0.63
    amen
    -0.60
     necks
    -0.59
    Spread
    -0.58
     quo
    -0.56
     disproportionately
    -0.56
    antage
    -0.56
     foe
    -0.56
     disproportion
    -0.55
    POSITIVE LOGITS
    ifiable
    1.02
    ifications
    1.00
    if
    0.86
    itia
    0.83
    ifi
    0.81
     kidding
    0.80
     desserts
    0.80
     finished
    0.79
    ified
    0.78
    released
    0.77
    Act Density 0.055%

    No Known Activations