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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific alphanumeric patterns or codes

    oai_token-act-pair · gpt-3.5-turbo

    special delimiters or markers in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.63
     leveraging
    -0.62
     DOE
    -0.62
    alties
    -0.62
     Siem
    -0.62
    cases
    -0.61
     Pulitzer
    -0.60
     Lauder
    -0.60
    orpor
    -0.59
     FIG
    -0.59
    POSITIVE LOGITS
    ombat
    0.89
     moderator
    0.89
     Reply
    0.88
     reply
    0.87
    Reply
    0.86
     replies
    0.85
    anon
    0.82
    Posted
    0.80
    76561
    0.79
     commenter
    0.77
    Act Density 0.239%

    No Known Activations