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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating searching or looking for information

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Looking for news you can trust."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lago
    -0.77
    anas
    -0.77
    nown
    -0.75
    itol
    -0.74
    icipated
    -0.73
    claimed
    -0.73
    orb
    -0.73
    meet
    -0.71
    upuncture
    -0.70
    interstitial
    -0.70
    POSITIVE LOGITS
     suspic
    0.79
     noses
    0.72
     Glass
    0.69
     headlights
    0.69
    ahead
    0.68
     cursor
    0.66
     unfocused
    0.64
     bored
    0.64
     shiny
    0.62
     metab
    0.62
    Act Density 0.026%

    No Known Activations