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

    Neuronpedia

    INDEX
    Explanations

    terms related to political entities or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "PTI"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flies
    -0.91
    hold
    -0.91
    bye
    -0.80
    cle
    -0.76
    weights
    -0.72
    bars
    -0.72
    mble
    -0.70
    perse
    -0.70
    ãĤ£
    -0.70
    nces
    -0.69
    POSITIVE LOGITS
    ypes
    0.95
    ION
    0.92
     Cruiser
    0.85
    EMBER
    0.84
    ember
    0.84
    OGR
    0.82
    itious
    0.80
    BN
    0.79
    WS
    0.78
    ARGET
    0.78
    Act Density 0.023%

    No Known Activations