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

    Neuronpedia

    INDEX
    Explanations

    words related to mechanics and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    specific metrics and measurements related to various contexts and subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earable
    -0.74
     Canaver
    -0.74
    ovember
    -0.71
     Nare
    -0.69
    ©¶æ
    -0.68
     Berks
    -0.66
    ndum
    -0.66
    ikarp
    -0.64
    >>>>>>>>
    -0.64
    odcast
    -0.64
    POSITIVE LOGITS
    worthiness
    1.30
     characteristics
    1.24
     size
    1.23
     quality
    1.22
     sizes
    1.20
     strengths
    1.17
     length
    1.13
     availability
    1.10
     responsiveness
    1.09
     qualities
    1.08
    Act Density 0.564%

    No Known Activations