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

    Neuronpedia

    INDEX
    Explanations

    numbers with words describing quantities or quantifiers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -0.72
    <bos>
    -0.69
    relenting
    -0.69
    ambiguation
    -0.67
     juges
    -0.63
     withal
    -0.63
     indescri
    -0.59
     pettico
    -0.59
     nachher
    -0.59
     nobly
    -0.59
    POSITIVE LOGITS
     kram
    0.93
     makro
    0.92
     plak
    0.90
     logis
    0.90
     ideolog
    0.90
     kac
    0.88
     praktik
    0.87
     zub
    0.87
     akut
    0.85
     ohr
    0.85
    Act Density 0.170%

    No Known Activations