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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people, places, and things

    oai_token-act-pair · gpt-3.5-turbo

    names or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.66
    ĸļ
    -0.65
    enegger
    -0.62
    anwhile
    -0.60
    mble
    -0.59
    ãĥ¼ãĥĨ
    -0.58
    代
    -0.55
    raints
    -0.53
    pherd
    -0.52
     referen
    -0.52
    POSITIVE LOGITS
    eland
    0.62
    Coin
    0.54
    coin
    0.53
    antz
    0.53
    anta
    0.52
    osh
    0.51
    OTA
    0.50
    ont
    0.50
    Net
    0.49
     Island
    0.48
    Act Density 0.927%

    No Known Activations