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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and perceptions of change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ant
    -0.17
     Bomb
    -0.15
    हल
    -0.15
    ify
    -0.15
    -uppercase
    -0.14
    ohl
    -0.14
    bomb
    -0.14
    ableView
    -0.14
    BUF
    -0.13
    ly
    -0.13
    POSITIVE LOGITS
    oppins
    0.18
    onte
    0.15
    stal
    0.15
    endale
    0.15
    ále
    0.14
    ียà¸ĩ
    0.14
    iaux
    0.14
    ìĿ´ìĹIJ
    0.14
    afone
    0.14
     Rao
    0.13
    Act Density 0.516%

    No Known Activations