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

    Neuronpedia

    INDEX
    Explanations

    negative or conditional phrases indicating uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    олаг
    -0.17
     kitten
    -0.15
    hos
    -0.15
    icine
    -0.15
    aber
    -0.14
    abouts
    -0.14
    rž
    -0.14
    xp
    -0.14
    ovah
    -0.14
    ESSAGES
    -0.14
    POSITIVE LOGITS
    ارت
    0.14
    UC
    0.14
     blockDim
    0.14
    \Carbon
    0.14
     <*
    0.13
    AFX
    0.13
     Bare
    0.13
    ient
    0.13
     Graf
    0.13
     Spatial
    0.13
    Act Density 0.001%

    No Known Activations