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

    Neuronpedia

    INDEX
    Explanations

    phrases where the word "that" is emphasized or highlighted

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.79
    ãĥł
    -0.79
    %%%%
    -0.75
    \\\\\\\\
    -0.75
    rees
    -0.73
    ãĥij
    -0.70
    ourses
    -0.69
    ãĥ¼ãĤ¯
    -0.68
     excerpts
    -0.68
    CLAIM
    -0.67
    POSITIVE LOGITS
    ched
    0.87
     kind
    0.82
    ching
    0.82
     damned
    0.81
     pesky
    0.76
     same
    0.74
     knack
    0.74
    cher
    0.73
    same
    0.70
     brill
    0.70
    Act Density 0.129%

    No Known Activations