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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns and entities such as names of companies, people, and places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to companies, organizations, or people's names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izoph
    -0.78
    âĶĢâĶĢâĶĢâĶĢ
    -0.74
    ãĤ¤ãĥĪ
    -0.73
    Ò
    -0.69
    ĺħ
    -0.69
    worldly
    -0.67
    ̶
    -0.65
    7601
    -0.64
    ãĤ¦ãĤ¹
    -0.63
    Ùħ
    -0.62
    POSITIVE LOGITS
     meanwhile
    1.37
     declined
    1.31
     spokesman
    1.29
     spokeswoman
    1.28
     also
    1.23
     denies
    1.11
     appealed
    1.07
     insists
    1.06
     responded
    1.04
     acknowledges
    1.02
    Act Density 0.749%

    No Known Activations