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

    Neuronpedia

    INDEX
    Explanations

    URLs or website links

    oai_token-act-pair · gpt-3.5-turbo

    URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.90
     trave
    -0.77
     Morse
    -0.74
     neighb
    -0.73
    Ļ½
    -0.71
     contrace
    -0.69
     deceive
    -0.67
     reluct
    -0.67
     grav
    -0.66
     territ
    -0.64
    POSITIVE LOGITS
    ://
    1.67
    :/
    1.07
    doi
    0.97
    archive
    0.92
    docs
    0.88
    twitter
    0.83
    natureconservancy
    0.82
    books
    0.75
    eline
    0.74
    hl
    0.73
    Act Density 0.015%

    No Known Activations