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

    Neuronpedia

    INDEX
    Explanations

    references to specific documents or textual sources

    oai_token-act-pair · gpt-3.5-turbo

    references to specific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.76
    avorite
    -0.75
    Stars
    -0.74
    akening
    -0.74
     Flavoring
    -0.72
    tones
    -0.71
    luster
    -0.70
    bye
    -0.69
    creen
    -0.69
    NetMessage
    -0.69
    POSITIVE LOGITS
    arians
    1.05
    arian
    1.05
     document
    0.98
    ually
    0.97
    document
    0.82
     documents
    0.81
    abal
    0.80
    urally
    0.75
     specifies
    0.75
    aires
    0.73
    Act Density 0.013%

    No Known Activations