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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating existence or presence of concepts related to uncertainty or unfulfilled conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adem
    -0.17
     بÙĪابة
    -0.16
    Ïģιά
    -0.15
    okes
    -0.15
    anza
    -0.14
    ruit
    -0.14
    abis
    -0.14
    bsp
    -0.14
    aversable
    -0.14
    obbies
    -0.14
    POSITIVE LOGITS
     can
    0.24
     lo
    0.24
     remain
    0.21
     exist
    0.20
     follow
    0.20
     do
    0.20
     need
    0.19
     seems
    0.18
     seem
    0.18
     Can
    0.17
    Act Density 0.089%

    No Known Activations