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

    Neuronpedia

    INDEX
    Explanations

    direct speech statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    quotations and reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stub
    -0.57
     harvest
    -0.54
     woodland
    -0.53
     fucking
    -0.52
    tumblr
    -0.52
     nig
    -0.51
     pneumonia
    -0.51
     broom
    -0.51
     mirac
    -0.50
     mole
    -0.49
    POSITIVE LOGITS
    aturday
    0.61
    uer
    0.59
    cients
    0.59
    inguished
    0.59
    ukong
    0.58
    enegger
    0.57
    iHUD
    0.56
    region
    0.56
    bnb
    0.56
    emi
    0.56
    Act Density 0.631%

    No Known Activations