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

    Neuronpedia

    INDEX
    Explanations

    phrases related to automated calls and phone communication issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĦ±
    -0.15
    979
    -0.15
    rez
    -0.15
    ç¹ģ
    -0.15
     Lesbian
    -0.14
    folio
    -0.14
     RTL
    -0.14
    RTL
    -0.14
     Sabb
    -0.14
    rtl
    -0.14
    POSITIVE LOGITS
     rob
    0.42
     Rob
    0.32
    Rob
    0.29
    rob
    0.27
     aut
    0.23
     unwanted
    0.23
     robot
    0.22
     te
    0.22
     spam
    0.22
     spoof
    0.21
    Act Density 0.001%

    No Known Activations