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

    Neuronpedia

    INDEX
    Explanations

    text written in a specific format: a colon followed by a statement or message

    oai_token-act-pair · gpt-3.5-turbo

    indicatives of written communication, such as quotes or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     principals
    -0.70
     adversaries
    -0.70
     reconc
    -0.69
     territ
    -0.67
     stride
    -0.65
     undermin
    -0.64
     glac
    -0.62
     spills
    -0.61
     visitation
    -0.61
     comprom
    -0.61
    POSITIVE LOGITS
     âĨij
    1.25
    Originally
    1.08
    Show
    1.05
     Originally
    1.04
     Quote
    1.03
    Quote
    0.99
     Hmm
    0.98
    Hi
    0.97
    Hello
    0.95
     Hey
    0.95
    Act Density 0.061%

    No Known Activations