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

    Neuronpedia

    INDEX
    Explanations

    references to citations or additional information

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" followed by variations of the word "the" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocking
    -0.70
    iola
    -0.67
    IPP
    -0.66
    rawdownloadcloneembedreportprint
    -0.64
    tun
    -0.64
    sky
    -0.63
    esi
    -0.62
    horn
    -0.62
    ashtra
    -0.61
    need
    -0.61
    POSITIVE LOGITS
     ensure
    0.94
     arrive
    0.83
     avoid
    0.83
     accompany
    0.82
     improve
    0.82
     accommodate
    0.81
     counteract
    0.81
    ggles
    0.81
     satisfy
    0.81
     maximize
    0.80
    Act Density 0.246%

    No Known Activations