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

    Neuronpedia

    INDEX
    Explanations

    instances of dishonesty or hypocrisy in people's behaviors and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     à¤Ĩन
    -0.14
    empl
    -0.14
    thern
    -0.14
    виÑĤ
    -0.14
     Tá»īnh
    -0.13
    ighth
    -0.13
    ITHER
    -0.13
    ê·Ģ
    -0.13
    polator
    -0.13
    (Void
    -0.13
    POSITIVE LOGITS
     behavior
    0.16
    è¡Į为
    0.15
     behaviour
    0.15
    esa
    0.14
    дейÑģÑĤв
    0.14
     Behavior
    0.14
     Banc
    0.14
    ãĥ¼ãĥ«ãĥī
    0.14
    iciencies
    0.13
    ekyll
    0.13
    Act Density 0.174%

    No Known Activations