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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ĵng
    -0.17
    metics
    -0.15
    ÑĨен
    -0.14
    à¸ļาà¸ĩ
    -0.14
     architectures
    -0.14
    amics
    -0.14
    roperties
    -0.13
     corresponding
    -0.13
     aantal
    -0.13
    achts
    -0.13
    POSITIVE LOGITS
     part
    0.31
     term
    0.26
     bit
    0.23
     result
    0.23
     continuation
    0.23
     descendant
    0.22
     attempt
    0.22
     culmination
    0.22
     blend
    0.22
     spin
    0.21
    Act Density 0.374%

    No Known Activations