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

    Neuronpedia

    INDEX
    Explanations

    terms related to military units, locations, and personnel

    oai_token-act-pair · gpt-3.5-turbo

    groups, organizations, and community structures related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥ
    -0.65
    ãĥĥãĥī
    -0.62
    Lear
    -0.62
    ãĥ³ãĤ¸
    -0.59
    ãĤ¸
    -0.57
    ãĤ¶
    -0.57
    Beg
    -0.56
    ãĥ£
    -0.55
    erb
    -0.54
    ãĤ°
    -0.54
    POSITIVE LOGITS
     converge
    1.11
     unite
    1.07
     collide
    1.07
     are
    1.04
     comprise
    1.03
     await
    1.01
     deserve
    1.00
     were
    0.99
     arrive
    0.99
     have
    0.98
    Act Density 0.545%

    No Known Activations