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

    Neuronpedia

    INDEX
    Explanations

    numbers with ascending order and possibly mathematical symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences and structured data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     laun
    -0.60
     acre
    -0.55
    Joy
    -0.55
    Americans
    -0.55
    acre
    -0.54
    880
    -0.53
    hon
    -0.53
    aunt
    -0.53
    ilts
    -0.52
    Way
    -0.52
    POSITIVE LOGITS
    thora
    0.65
    ulia
    0.65
     ¯
    0.63
    ĺħ
    0.62
    âĶĢâĶĢâĶĢâĶĢ
    0.62
     ÎĶ
    0.61
     Pirate
    0.61
     ;;
    0.60
     TOTAL
    0.60
     :=
    0.60
    Act Density 0.037%

    No Known Activations