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

    Neuronpedia

    INDEX
    Explanations

    phrases centered around a specific location or topic

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to focus or emphasis on a specific subject or area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.71
    LV
    -0.66
    ggies
    -0.66
     ABE
    -0.64
    Calif
    -0.63
    TN
    -0.63
    =-=-=-=-=-=-=-=-
    -0.62
    ãĤĬ
    -0.62
    ãĥīãĥ©
    -0.62
    thur
    -0.62
    POSITIVE LOGITS
     centered
    1.04
    olars
    0.79
    SHIP
    0.77
     revolves
    0.75
     revolving
    0.74
     atop
    0.74
    iflower
    0.72
    rals
    0.72
     toward
    0.71
    iosity
    0.71
    Act Density 0.010%

    No Known Activations