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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate perception or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å®Ļ
    -0.17
    AWN
    -0.15
    äºĪ
    -0.15
    .shell
    -0.15
     Ore
    -0.14
    utenberg
    -0.14
    illin
    -0.13
    irsch
    -0.13
    ATT
    -0.13
    iu
    -0.13
    POSITIVE LOGITS
    incerely
    0.15
    .toObject
    0.15
    662
    0.14
     faint
    0.14
    785
    0.14
    ाब
    0.14
    684
    0.14
    474
    0.13
    ernote
    0.13
    chema
    0.13
    Act Density 0.111%

    No Known Activations