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

    Neuronpedia

    INDEX
    Explanations

    significant relationships between data points and their respective categories or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.65
    parsedMessage
    -0.59
    PreferredItem
    -0.53
     snippetHide
    -0.53
     houſe
    -0.52
    舺
    -0.50
    Gön
    -0.49
     nakalista
    -0.48
    TypedDataSet
    -0.48
     Estación
    -0.46
    POSITIVE LOGITS
    GOTREF
    0.40
     насколько
    0.36
    ніципалі
    0.35
     defStyle
    0.33
    ConfigureAwait
    0.32
     marginBottom
    0.32
    تقاوى
    0.32
    новниш
    0.31
     Embar
    0.31
    ServerError
    0.31
    Act Density 1.365%

    No Known Activations