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

    Neuronpedia

    INDEX
    Explanations

    phrases related to categories, classifications, or divisions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bracket" and similar terms related to structured formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.81
     Soy
    -0.69
     Nare
    -0.67
     Antar
    -0.63
    uv
    -0.62
     Gest
    -0.61
     Loch
    -0.60
     Traffic
    -0.60
     VIDEOS
    -0.58
    vez
    -0.57
    POSITIVE LOGITS
     brackets
    1.17
     bracket
    1.16
    ackets
    1.06
    acket
    0.98
    uled
    0.83
    halla
    0.76
    sheets
    0.75
    agy
    0.75
    ashtra
    0.73
    uling
    0.72
    Act Density 0.008%

    No Known Activations