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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word 'tone' and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.17
    ly
    -0.17
    opper
    -0.16
    orsch
    -0.15
     potent
    -0.15
    rene
    -0.15
    ustin
    -0.15
    min
    -0.15
    iable
    -0.15
    auc
    -0.14
    POSITIVE LOGITS
    ality
    0.19
    ymoon
    0.17
    ouver
    0.16
    nage
    0.16
    ovan
    0.16
    ned
    0.16
    ález
    0.15
    terra
    0.15
    bsp
    0.15
    Ton
    0.15
    Act Density 0.035%

    No Known Activations