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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly related to events, organizations, and places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events or entities, particularly in sports and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibles
    -0.57
    ãĥ³ãĤ¸
    -0.56
     guiActiveUn
    -0.55
    Pg
    -0.54
    ãĤ§
    -0.48
    âĸ¬âĸ¬
    -0.48
     voic
    -0.48
     tattoo
    -0.47
    Nar
    -0.47
    ibly
    -0.46
    POSITIVE LOGITS
     respectively
    0.62
    .''.
    0.58
    .
    0.56
     Tinker
    0.51
    .[
    0.51
     Alexandria
    0.51
     supplemented
    0.50
     Senegal
    0.49
    ãĢĤ
    0.47
    clave
    0.47
    Act Density 1.561%

    No Known Activations