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

    Neuronpedia

    INDEX
    Explanations

    dates or time references in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "when"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    whatever
    -0.78
    ertain
    -0.76
    vre
    -0.69
    ouble
    -0.68
    urden
    -0.67
    \\\\\\\\
    -0.67
    ktop
    -0.66
    ivot
    -0.65
    atown
    -0.64
    nex
    -0.64
    POSITIVE LOGITS
    soever
    0.99
    upon
    0.93
     someone
    0.84
     confronted
    0.79
     suddenly
    0.75
     they
    0.74
     hordes
    0.73
     somebody
    0.72
     reporters
    0.71
     researchers
    0.70
    Act Density 0.108%

    No Known Activations