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

    Neuronpedia

    INDEX
    Explanations

    phrases related to processes or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that define or describe various concepts and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Units
    -0.71
     mathemat
    -0.71
     intrins
    -0.67
     stances
    -0.66
     contrace
    -0.65
     acquisitions
    -0.64
     verbs
    -0.64
     Dragonbound
    -0.63
     viewpoints
    -0.62
     engagements
    -0.62
    POSITIVE LOGITS
    pload
    0.87
    ģ«
    0.85
    emaker
    0.84
    ŃĶ
    0.82
    ogram
    0.81
    worth
    0.77
    wana
    0.77
    ritten
    0.76
    agraph
    0.75
    itialized
    0.74
    Act Density 0.334%

    No Known Activations