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

    Neuronpedia

    INDEX
    Explanations

    words containing the specific string "TR"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    manship
    -0.82
    soever
    -0.79
    âĸ¬âĸ¬
    -0.76
    tons
    -0.69
     Formula
    -0.66
     arts
    -0.66
    creen
    -0.63
    fighter
    -0.61
     sterling
    -0.60
    ces
    -0.59
    POSITIVE LOGITS
    UTH
    1.43
    ACK
    1.02
    ickle
    1.02
    acker
    0.99
    UST
    0.98
    UCK
    0.98
    ainer
    0.95
    usted
    0.94
    acing
    0.94
    umble
    0.93
    Act Density 0.028%

    No Known Activations