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
    emmel
    -0.15
    hof
    -0.15
    amp
    -0.14
    628
    -0.14
    ittest
    -0.14
    haven
    -0.13
    able
    -0.13
     edt
    -0.13
     оÑĩ
    -0.13
    zech
    -0.13
    POSITIVE LOGITS
    linky
    0.18
    ãĤĬ
    0.17
    /is
    0.16
    nt
    0.15
    rale
    0.15
    rian
    0.14
    agan
    0.14
    itag
    0.14
    alion
    0.14
    esseract
    0.14
    Act Density 0.121%

    No Known Activations