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

    Neuronpedia

    INDEX
    Explanations

    clear and significant descriptors related to qualities and differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.65
    UserScript
    -0.52
    ValueStyle
    -0.43
     IFTT
    -0.43
     Agustus
    -0.43
     czasem
    -0.43
     cafetería
    -0.43
     kaarangay
    -0.43
    はじめに
    -0.42
     disambiguazione
    -0.42
    POSITIVE LOGITS
     strongly
    0.65
     heavily
    0.60
     sekali
    0.55
     deeply
    0.54
     Strongly
    0.54
     greatly
    0.53
     strict
    0.53
    strongly
    0.52
    Strongly
    0.52
     מאוד
    0.52
    Act Density 0.761%

    No Known Activations