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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proposed methods and approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    various proposed methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.70
     queſta
    -0.63
    +#+
    -0.62
    parsedMessage
    -0.61
     houſe
    -0.60
     Houſe
    -0.56
    :✨
    -0.56
    styleType
    -0.56
    artifactId
    -0.54
    mtrl
    -0.54
    POSITIVE LOGITS
     methods
    0.55
     schemes
    0.52
     forskjellige
    0.51
     forskellige
    0.50
     Methoden
    0.50
     ulike
    0.49
     different
    0.47
    hæng
    0.46
     olika
    0.45
     różne
    0.45
    Act Density 0.123%

    No Known Activations