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

    Neuronpedia

    INDEX
    Explanations

    references to structured assistance programs or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ample
    -0.16
    amples
    -0.15
     Cure
    -0.15
    cete
    -0.15
    adal
    -0.14
    aket
    -0.14
    riday
    -0.14
    imate
    -0.14
    ulan
    -0.14
    åłĤ
    -0.14
    POSITIVE LOGITS
    roje
    0.17
    ovi
    0.15
    amin
    0.14
    alan
    0.14
     bleach
    0.14
     Bab
    0.14
     contrary
    0.14
    .scalablytyped
    0.13
    ëłĪ
    0.13
    amel
    0.13
    Act Density 0.024%

    No Known Activations