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

    Neuronpedia

    INDEX
    Explanations

    predictions or expectations of future events

    oai_token-act-pair · gpt-3.5-turbo

    the conditional or future tense usage of the word "would"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.65
     Sets
    -0.63
    pires
    -0.61
     Kag
    -0.60
    RD
    -0.58
    Building
    -0.56
     Kis
    -0.55
    building
    -0.55
    /.
    -0.55
     Reporting
    -0.54
    POSITIVE LOGITS
     be
    1.17
    soon
    1.11
     eventually
    0.98
     prevail
    0.94
    meet
    0.93
     someday
    0.90
     sooner
    0.90
     gladly
    0.90
     inevitably
    0.89
    ĸļ
    0.88
    Act Density 0.148%

    No Known Activations