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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of disbelief or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yu
    -0.17
    yz
    -0.15
    yar
    -0.14
     ä¸ĸçķĮ
    -0.14
    aat
    -0.14
    ying
    -0.14
    éĥİ
    -0.14
    oton
    -0.14
    005
    -0.14
    389
    -0.14
    POSITIVE LOGITS
     been
    0.19
    кÑĥÑĤ
    0.16
     recently
    0.16
    iversit
    0.15
     come
    0.15
    insk
    0.15
     lately
    0.15
    assy
    0.15
     sido
    0.15
    CONDITION
    0.15
    Act Density 0.082%

    No Known Activations