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

    Neuronpedia

    INDEX
    Explanations

    references to evil or malevolent actions and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icle
    -0.16
    etch
    -0.16
    ero
    -0.16
    anda
    -0.15
    ĤŃ
    -0.14
     пок
    -0.14
    ulong
    -0.14
    Loads
    -0.14
    laus
    -0.14
    aison
    -0.14
    POSITIVE LOGITS
     deeds
    0.19
    -do
    0.16
    ness
    0.16
     deed
    0.16
    ution
    0.16
    reds
    0.15
    indre
    0.15
    측
    0.15
    äºİ
    0.15
    nature
    0.14
    Act Density 0.045%

    No Known Activations