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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical specifications or details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     duel
    -0.67
     gorilla
    -0.66
     bills
    -0.62
     obsc
    -0.61
     tighter
    -0.60
     dred
    -0.60
     lobb
    -0.58
     gays
    -0.58
     Dod
    -0.58
     Origin
    -0.58
    POSITIVE LOGITS
    CI
    0.96
    NE
    0.94
    ENG
    0.94
    WB
    0.94
    CIA
    0.93
    OPS
    0.92
    CN
    0.90
    1000
    0.89
    OP
    0.88
    RH
    0.87
    Act Density 0.020%

    No Known Activations