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

    Neuronpedia

    INDEX
    Explanations

    references to writing instruments, particularly pens

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "pen" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndum
    -0.76
    ONEY
    -0.73
    IELD
    -0.72
     Lumpur
    -0.71
    ONSORED
    -0.70
    enance
    -0.70
    «ĺ
    -0.64
     Benef
    -0.63
     disadvant
    -0.62
    rians
    -0.62
    POSITIVE LOGITS
    ultimate
    1.42
    itent
    1.39
    cil
    1.14
    manship
    1.13
    insula
    1.07
    elope
    1.06
    ning
    1.01
    cill
    0.99
    nington
    0.98
     pen
    0.95
    Act Density 0.014%

    No Known Activations