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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "had" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     now
    -0.20
     hereby
    -0.18
     currently
    -0.17
    able
    -0.17
    yah
    -0.16
    dsn
    -0.16
    ands
    -0.16
    OMET
    -0.16
    اÙī
    -0.14
    conde
    -0.14
    POSITIVE LOGITS
     originally
    0.32
     earlier
    0.25
    nt
    0.25
     hoped
    0.24
    Originally
    0.23
     Originally
    0.23
    ness
    0.22
     Earlier
    0.22
    /is
    0.21
    origin
    0.21
    Act Density 0.130%

    No Known Activations