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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with "Each" and describe individual items or elements belonging to a group

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to representation and challenges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WM
    -0.70
    qus
    -0.67
    rers
    -0.65
     abound
    -0.63
     Curt
    -0.62
     Farrell
    -0.62
    Ws
    -0.62
     Bron
    -0.61
    dm
    -0.61
    paren
    -0.59
    POSITIVE LOGITS
     individually
    1.44
     separately
    1.15
     independently
    0.98
     unique
    0.98
     varying
    0.89
     distinct
    0.88
     differing
    0.86
     uniquely
    0.84
     differently
    0.82
     respective
    0.79
    Act Density 0.290%

    No Known Activations