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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical conditions, especially those involving performance or barriers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to impotence and barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.73
     Saras
    -0.71
     ribbon
    -0.68
    BUG
    -0.65
    SOURCE
    -0.62
    byn
    -0.62
    ãĤ´ãĥ³
    -0.60
     Today
    -0.60
    baum
    -0.60
     Puzzles
    -0.60
    POSITIVE LOGITS
    inence
    0.81
    etr
    0.73
    itely
    0.72
     perjury
    0.70
    eties
    0.70
    urity
    0.68
    ados
    0.68
    achment
    0.67
    hesive
    0.67
    enza
    0.65
    Act Density 0.064%

    No Known Activations