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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a final decision or judgment

    oai_token-act-pair · gpt-3.5-turbo

    common conjunctions and prepositions that indicate relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¶
    -0.64
    Ĥª
    -0.61
    obal
    -0.60
    hler
    -0.55
    KING
    -0.55
    ãĥ¼ãĥ
    -0.54
    teness
    -0.53
    argon
    -0.51
    ãĥ«
    -0.50
     Oath
    -0.50
    POSITIVE LOGITS
    ;
    1.02
    .
    1.01
     during
    1.00
    .</
    0.99
    .—
    0.98
    !
    0.98
    .[
    0.97
    !,
    0.95
     lest
    0.95
     ;)
    0.94
    Act Density 1.069%

    No Known Activations