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

    Neuronpedia

    INDEX
    Explanations

    quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "said" indicating reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spir
    -0.78
    erity
    -0.76
    mol
    -0.76
    etheless
    -0.76
    enfranch
    -0.73
     reunited
    -0.73
    thur
    -0.69
     tolerated
    -0.68
     neighb
    -0.67
     fertil
    -0.66
    POSITIVE LOGITS
     Sgt
    0.87
     Diane
    0.81
     Vick
    0.79
     Andy
    0.78
     Geoff
    0.76
     analyst
    0.75
     Dawn
    0.75
     Andrea
    0.75
     Mike
    0.75
     Chuck
    0.75
    Act Density 0.063%

    No Known Activations