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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Advance
    -0.15
    egas
    -0.14
    visor
    -0.14
    หว
    -0.14
    ponse
    -0.14
    .connections
    -0.14
    riterion
    -0.14
    ships
    -0.13
    islav
    -0.13
    Advance
    -0.13
    POSITIVE LOGITS
     operation
    0.42
     use
    0.41
     play
    0.39
     existence
    0.38
     circulation
    0.34
    operation
    0.32
     motion
    0.31
     question
    0.30
     action
    0.29
    use
    0.29
    Act Density 0.246%

    No Known Activations