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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thought" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igner
    -0.15
    ei
    -0.15
    antz
    -0.14
    ãĥ«ãĥĪ
    -0.14
    ả
    -0.14
    elsius
    -0.14
    inq
    -0.14
     GK
    -0.14
    bla
    -0.14
    ¯
    -0.14
    POSITIVE LOGITS
    fully
    0.25
     perhaps
    0.24
     surely
    0.24
     maybe
    0.24
    lessly
    0.22
    maybe
    0.21
    fulness
    0.21
    perhaps
    0.21
     Maybe
    0.19
     Perhaps
    0.19
    Act Density 0.024%

    No Known Activations