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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating representation or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate representation or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jar
    -0.64
    intend
    -0.61
    ita
    -0.61
    roit
    -0.60
    imb
    -0.60
    ibel
    -0.60
    erm
    -0.60
    erman
    -0.60
     behaved
    -0.60
    ithing
    -0.60
    POSITIVE LOGITS
    Interstitial
    0.83
     an
    0.77
     a
    0.73
     something
    0.70
    orically
    0.68
    reement
    0.67
    Operation
    0.66
     sacrifices
    0.66
     salvation
    0.66
    agi
    0.66
    Act Density 0.072%

    No Known Activations