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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "started" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oms
    -0.16
    gmt
    -0.16
    gem
    -0.14
    /function
    -0.14
    itin
    -0.14
    .policy
    -0.14
    mainwindow
    -0.14
     McCl
    -0.14
    ighter
    -0.13
     Cage
    -0.13
    POSITIVE LOGITS
    ossa
    0.15
    punkt
    0.15
    byn
    0.14
     Robbins
    0.14
    ReadStream
    0.14
     Strand
    0.14
    ONGL
    0.14
    hrad
    0.14
    anian
    0.14
    anic
    0.14
    Act Density 0.039%

    No Known Activations