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

    Neuronpedia

    INDEX
    Explanations

    statements where someone is conveying information

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.78
    greg
    -0.71
    EMBER
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
    Ü
    -0.70
    åĤ
    -0.69
    scribe
    -0.69
    ãĥĺ
    -0.68
    Tank
    -0.67
    aceae
    -0.65
    POSITIVE LOGITS
     although
    1.36
     despite
    1.15
     "[
    1.14
     while
    1.09
     whilst
    0.98
     unlike
    0.94
     whereas
    0.92
     unless
    0.89
     "âĢ¦
    0.84
     since
    0.83
    Act Density 0.196%

    No Known Activations