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

    Neuronpedia

    INDEX
    Explanations

    instances of deception and manipulation, particularly in the context of technology and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cur
    -0.17
    ighth
    -0.16
    avr
    -0.15
    aus
    -0.14
    Cur
    -0.14
    avez
    -0.14
    phant
    -0.14
     Wilkinson
    -0.14
     Ment
    -0.14
     benef
    -0.13
    POSITIVE LOGITS
    adol
    0.15
     unsus
    0.15
     BitConverter
    0.15
    urette
    0.14
     apo
    0.14
    641
    0.14
    /cms
    0.14
    lingen
    0.14
    ondon
    0.14
    ndl
    0.14
    Act Density 0.328%

    No Known Activations