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

    Neuronpedia

    INDEX
    Explanations

    strong action verbs with specific endings

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.72
     Oath
    -0.65
     pony
    -0.63
    LOD
    -0.63
    ],"
    -0.62
     SEAL
    -0.60
    ħĭ
    -0.59
    tnc
    -0.59
    )",
    -0.58
     clipboard
    -0.56
    POSITIVE LOGITS
    quartered
    0.98
    ually
    0.96
    cially
    0.94
    itting
    0.94
    cknowled
    0.94
    ifully
    0.93
    rarily
    0.93
    ately
    0.93
    itionally
    0.93
    ially
    0.90
    Act Density 0.276%

    No Known Activations