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

    Neuronpedia

    INDEX
    Explanations

    words that indicate modification or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inverse
    -0.37
     teor
    -0.37
     Inverse
    -0.33
     recarg
    -0.32
    inputValue
    -0.32
    inverse
    -0.31
    Inverse
    -0.30
    CPtr
    -0.30
    tn
    -0.30
    UNDEFINED
    -0.29
    POSITIVE LOGITS
    ckså
    0.91
    featureID
    0.89
     estekak
    0.68
    writeFieldEnd
    0.65
     AssemblyCulture
    0.62
    RegistryLite
    0.61
     alſo
    0.60
     additionally
    0.59
     ProtoMessage
    0.58
    MessageOf
    0.57
    Act Density 0.475%

    No Known Activations