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

    Neuronpedia

    INDEX
    Explanations

    comma-separated lists of phrases

    oai_token-act-pair · gpt-3.5-turbo

    commas, indicating lists or additional information within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.62
    ²¾
    -0.62
    antz
    -0.61
    aughs
    -0.59
    roxy
    -0.59
    tsy
    -0.58
    ¬¼
    -0.58
    Includes
    -0.58
    EStreamFrame
    -0.56
    aceae
    -0.56
    POSITIVE LOGITS
     meanwhile
    2.05
     however
    1.75
     moreover
    1.47
     meantime
    1.31
     incidentally
    1.25
     unsurprisingly
    1.24
     furthermore
    1.19
     though
    1.15
     likewise
    1.14
     therefore
    1.12
    Act Density 0.228%

    No Known Activations