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

    Neuronpedia

    INDEX
    Explanations

    words related to important structural or supportive elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to foundational concepts or essential elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DIT
    -0.86
    displayText
    -0.81
    ãĤ±
    -0.80
    ivil
    -0.78
     Dragonbound
    -0.76
    ells
    -0.75
    LOAD
    -0.74
    thel
    -0.73
    enegger
    -0.72
    lyss
    -0.71
    POSITIVE LOGITS
     pillar
    1.19
     pillars
    1.14
     Pillar
    0.78
    stones
    0.77
     maiden
    0.75
     fide
    0.74
    OPLE
    0.69
     squid
    0.68
     bowling
    0.67
     plank
    0.66
    Act Density 0.006%

    No Known Activations