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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prefer to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tén
    -0.38
     התק
    -0.37
    いしい
    -0.37
    Captor
    -0.37
     appearances
    -0.37
    IActionResult
    -0.36
     Codable
    -0.36
    BIP
    -0.36
     stretchy
    -0.35
     הוד
    -0.35
    POSITIVE LOGITS
     prefer
    0.92
     Prefer
    0.86
     liever
    0.85
    prefer
    0.83
    Prefer
    0.81
     prefers
    0.76
     preferring
    0.75
     préfère
    0.74
    preferred
    0.73
    rather
    0.71
    Act Density 0.002%

    No Known Activations