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

    Neuronpedia

    INDEX
    Explanations

    specific formatting and submission requirements for documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bery
    -0.15
    еÑĢÑĪ
    -0.15
    adele
    -0.14
    addir
    -0.14
    enheim
    -0.14
    artment
    -0.13
    lete
    -0.13
    eyim
    -0.13
    xs
    -0.13
     anth
    -0.13
    POSITIVE LOGITS
     maximum
    0.26
    maximum
    0.22
     Arial
    0.21
    Arial
    0.21
     Maximum
    0.21
    Maximum
    0.21
     Times
    0.20
     max
    0.20
     Word
    0.19
    Word
    0.18
    Act Density 0.029%

    No Known Activations