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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest recommendations or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.21
    ellig
    -0.17
    äºŃ
    -0.16
    ÑĶм
    -0.15
    encion
    -0.15
    iggins
    -0.15
    -fontawesome
    -0.15
    ungeon
    -0.15
    миÑĢ
    -0.14
    asics
    -0.14
    POSITIVE LOGITS
     check
    0.32
    check
    0.29
     consider
    0.29
    try
    0.28
     look
    0.27
     try
    0.27
     Consider
    0.26
     nothing
    0.25
    -check
    0.24
     Check
    0.24
    Act Density 0.063%

    No Known Activations