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

    Neuronpedia

    INDEX
    Explanations

    paragraphs starting with the word "Here."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Here" followed by a numerical context or list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grace
    -0.74
     acupuncture
    -0.65
     hygiene
    -0.65
    \">
    -0.62
    omore
    -0.60
     LSD
    -0.58
    omedical
    -0.55
    offensive
    -0.55
    ped
    -0.55
     healing
    -0.54
    POSITIVE LOGITS
    tics
    1.19
    tical
    1.08
    here
    1.07
    abouts
    1.04
    tic
    0.99
     Transcript
    0.84
     newsp
    0.83
     Comes
    0.83
    orer
    0.76
    herer
    0.75
    Act Density 0.020%

    No Known Activations