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

    Neuronpedia

    INDEX
    Explanations

    references to specific or particular items or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "specifically."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Isles
    -0.81
    ulton
    -0.74
    anon
    -0.71
    lyn
    -0.71
     Kenn
    -0.64
    Afee
    -0.64
    ILY
    -0.64
    ocene
    -0.63
    izoph
    -0.61
    former
    -0.61
    POSITIVE LOGITS
     tailored
    1.02
     targeted
    0.98
     exempted
    0.88
     formulated
    0.87
     designed
    0.86
     geared
    0.85
     suited
    0.84
     tuned
    0.83
     targeting
    0.83
     engineered
    0.82
    Act Density 0.022%

    No Known Activations