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

    Neuronpedia

    INDEX
    Explanations

    keywords related to armed conflict

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "raw" materials or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŃĶ
    -0.84
    ately
    -0.74
    uated
    -0.70
    uate
    -0.70
     Amend
    -0.70
    ucky
    -0.67
     intercept
    -0.64
    ossession
    -0.63
     bubble
    -0.62
    utes
    -0.62
    POSITIVE LOGITS
    raw
    1.15
    esome
    0.89
    RAW
    0.87
    hide
    0.87
    lings
    0.87
    ls
    0.86
    TPPStreamerBot
    0.82
    pees
    0.81
    berries
    0.81
    lers
    0.81
    Act Density 0.003%

    No Known Activations