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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, possibly names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Billie" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sshd
    -0.71
    Wan
    -0.62
     Grayson
    -0.60
     beware
    -0.59
    hiba
    -0.59
    :#
    -0.58
    DEV
    -0.57
     FANTASY
    -0.55
    ORGE
    -0.55
    obook
    -0.54
    POSITIVE LOGITS
    anwhile
    0.62
    rill
    0.60
    swick
    0.60
    urches
    0.59
    EStream
    0.58
    rium
    0.58
    gery
    0.58
    lehem
    0.56
     Genocide
    0.55
    bas
    0.55
    Act Density 0.359%

    No Known Activations