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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to various entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'l'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¯ãĥ³
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.66
     spirited
    -0.65
     compensated
    -0.63
    PDATE
    -0.61
    çĭ
    -0.61
     stoked
    -0.61
    ħĭ
    -0.60
    éĹĺ
    -0.60
     patiently
    -0.60
    POSITIVE LOGITS
    ayers
    1.11
    ibraries
    1.09
    ounge
    1.09
    opez
    1.08
    oyd
    1.08
    anguages
    1.07
    ocated
    1.07
    ateral
    1.06
    ifestyle
    1.05
    ibrarian
    1.04
    Act Density 0.057%

    No Known Activations