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

    Neuronpedia

    INDEX
    Explanations

    company names and locations

    oai_token-act-pair · gpt-3.5-turbo

    empty or end-of-text tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }.
    -0.89
    _.
    -0.76
    >.
    -0.74
    $.
    -0.72
    ãĢĤ
    -0.72
    +.
    -0.70
    é¾įå
    -0.69
    !.
    -0.68
    *.
    -0.67
    .).
    -0.64
    POSITIVE LOGITS
     has
    0.59
     announced
    0.56
     welcomes
    0.56
     awoke
    0.56
     announces
    0.54
     watchdog
    0.54
     believes
    0.51
     reacted
    0.51
     surged
    0.50
     unveiled
    0.50
    Act Density 1.212%

    No Known Activations