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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating addition or extra information

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases involving the word "well."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hip
    -0.75
    rush
    -0.75
    anos
    -0.72
    iolet
    -0.66
    absolute
    -0.66
    mare
    -0.65
    ombo
    -0.64
    terness
    -0.64
    SHIP
    -0.62
    İĭ
    -0.61
    POSITIVE LOGITS
    ________________________________________________________________
    0.70
     suited
    0.68
     behaved
    0.68
     liked
    0.67
    ortment
    0.65
    ãĤ¶
    0.63
    above
    0.63
    FontSize
    0.63
    epad
    0.62
    ×ķ
    0.62
    Act Density 0.044%

    No Known Activations