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

    Neuronpedia

    INDEX
    Explanations

    concepts related to deception and betrayal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IZED
    -0.15
    ALLY
    -0.14
    regon
    -0.14
    ÑģÑĤеÑĢ
    -0.14
    ARGIN
    -0.13
    osate
    -0.13
    emu
    -0.13
    raig
    -0.13
    uzzer
    -0.13
    olest
    -0.13
    POSITIVE LOGITS
    ing
    1.75
    ING
    1.02
    ingt
    0.68
    ingen
    0.54
    инг
    0.54
    ë§ģ
    0.48
    ãĥ³ãĤ°
    0.47
    ting
    0.46
    ings
    0.46
    ingo
    0.46
    Act Density 0.513%

    No Known Activations