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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exceptions or unusual cases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gings
    -0.16
    beth
    -0.15
     Ara
    -0.15
    gie
    -0.15
    going
    -0.14
    inar
    -0.14
    inds
    -0.14
    age
    -0.14
    hest
    -0.13
    ichel
    -0.13
    POSITIVE LOGITS
    ively
    0.29
    ably
    0.19
    ities
    0.18
    enler
    0.18
    /errors
    0.17
    ìĤ¬íķŃ
    0.16
    nelle
    0.16
    ually
    0.16
    ality
    0.15
    ãĤº
    0.15
    Act Density 0.024%

    No Known Activations