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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "for" in various contexts

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

    "For" followed by a reason, example, or instance

    np_acts-logits-general · gemini-2.0-flash

    introducing examples or instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.62
     and
    -0.55
     muualla
    -0.52
    購入した
    -0.52
    /
    -0.51
    大満足
    -0.50
     or
    -0.49
    encodeWith
    -0.48
    作って
    -0.46
    awaiter
    -0.46
    POSITIVE LOGITS
     example
    1.33
     purposes
    1.25
     instance
    1.22
    tifying
    1.03
    tifies
    1.02
    geries
    0.99
    tify
    0.99
     reasons
    0.99
    erun
    0.99
    purposes
    0.98
    Act Density 0.555%

    No Known Activations