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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to approval or value judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aguda
    -0.52
    DeleteCommand
    -0.48
     Lambert
    -0.47
     hot
    -0.46
    Ecc
    -0.45
    
    -0.45
    り返
    -0.45
    vezető
    -0.45
    /******/
    -0.45
     financières
    -0.43
    POSITIVE LOGITS
    ization
    1.70
    化
    1.57
    isation
    1.50
    ized
    1.36
    izing
    1.35
     hóa
    1.27
    IZATION
    1.21
    izations
    1.21
    化的
    1.19
    ize
    1.18
    Act Density 0.373%

    No Known Activations