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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technological and scientific concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipled
    -0.66
    gov
    -0.59
    ornings
    -0.58
     Edited
    -0.55
    Specific
    -0.55
    olute
    -0.54
    verified
    -0.52
    cellaneous
    -0.52
    ificantly
    -0.52
     Important
    -0.51
    POSITIVE LOGITS
    iest
    0.72
    osphere
    0.68
    forts
    0.63
    liest
    0.63
    hest
    0.63
     movement
    0.63
     outweigh
    0.60
     brigade
    0.59
     moniker
    0.57
     menace
    0.56
    Act Density 1.192%

    No Known Activations