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

    Neuronpedia

    INDEX
    Explanations

    instances of numbers and technical terms related to a structured text or study

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     sappi
    -1.32
     scopri
    -1.06
     migli
    -0.94
     Augu
    -0.92
     PLW
    -0.91
     abbra
    -0.91
     rispond
    -0.91
     dichi
    -0.90
     affez
    -0.90
     dora
    -0.90
    POSITIVE LOGITS
     and
    0.82
     or
    0.76
     и
    0.70
     và
    0.69
    以及
    0.67
     или
    0.66
    bibnamefont
    0.64
     versus
    0.63
    和
    0.63
    และ
    0.62
    Act Density 0.216%

    No Known Activations