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

    Neuronpedia

    INDEX
    Explanations

    technical and scientific terms, particularly related to physics and electronics

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments towards modern concepts and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALT
    -0.68
    anth
    -0.64
     iT
    -0.64
    ËĪ
    -0.64
    Legend
    -0.63
    aband
    -0.63
    jan
    -0.61
    ãĥ´ãĤ¡
    -0.61
    kj
    -0.61
    ãĤ¨ãĥ«
    -0.61
    POSITIVE LOGITS
     alike
    1.55
     respectively
    1.43
     depending
    0.82
     sectors
    0.77
     approaches
    0.68
     simultaneously
    0.67
     interchange
    0.66
     industries
    0.64
     wings
    0.63
     environments
    0.61
    Act Density 0.560%

    No Known Activations