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

    Neuronpedia

    INDEX
    Explanations

    phrases related to additional, secondary, or hidden aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to "side" in various contexts, often relating to side careers, projects, or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.89
    yssey
    -0.89
    ESCO
    -0.87
    ãĤ¼ãĤ¦ãĤ¹
    -0.87
    ãģ®éŃĶ
    -0.83
    iott
    -0.78
    ancies
    -0.76
    uracy
    -0.75
    initions
    -0.71
    æ©Ł
    -0.71
    POSITIVE LOGITS
    kick
    1.00
    side
    0.87
     side
    0.81
     Side
    0.77
    board
    0.77
     lobe
    0.76
    Side
    0.76
     ups
    0.76
    por
    0.76
    burn
    0.75
    Act Density 0.025%

    No Known Activations