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

    Neuronpedia

    INDEX
    Explanations

    instances of words with apostrophes, indicating contractions or possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensation
    -0.14
    adiator
    -0.14
    elden
    -0.14
    hind
    -0.14
    _warnings
    -0.14
     BroadcastReceiver
    -0.14
     Herrera
    -0.14
     asm
    -0.13
    å¢ĥ
    -0.13
     Beam
    -0.13
    POSITIVE LOGITS
    ezier
    0.17
    oz
    0.15
     rall
    0.15
    evin
    0.14
    roup
    0.14
    auge
    0.13
    nonce
    0.13
    بÙĪÙĦ
    0.13
     pied
    0.13
     CHIP
    0.13
    Act Density 0.036%

    No Known Activations