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

    Neuronpedia

    INDEX
    Explanations

    words associated with controversy or significant reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apult
    -0.15
     pokoj
    -0.14
     DISCLAIMER
    -0.14
    ihilation
    -0.14
    lops
    -0.13
    erg
    -0.13
    laz
    -0.13
    spor
    -0.13
     Mey
    -0.13
    é¨ĵ
    -0.13
    POSITIVE LOGITS
     comm
    0.41
     stir
    0.37
     fur
    0.36
     hull
    0.35
     fuss
    0.32
     ker
    0.32
     hue
    0.31
     hub
    0.30
    fur
    0.29
     hoop
    0.29
    Act Density 0.173%

    No Known Activations