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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is quoted as saying something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating direct quotations or reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spir
    -0.84
    thur
    -0.81
    etheless
    -0.80
    mol
    -0.77
    erity
    -0.71
    successfully
    -0.69
    cffffcc
    -0.68
    ãĥİ
    -0.68
     neighb
    -0.67
    eneg
    -0.67
    POSITIVE LOGITS
     Diane
    0.85
     Sgt
    0.85
     Mike
    0.80
     Vick
    0.80
     Geoff
    0.80
     Dave
    0.79
     Donna
    0.79
     Chris
    0.78
     Dawn
    0.77
     Andrea
    0.76
    Act Density 0.056%

    No Known Activations