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

    Neuronpedia

    INDEX
    Explanations

    mentions of plans, intentions, or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tut
    -0.17
     Spot
    -0.16
    Closure
    -0.15
     |_|
    -0.14
    onomy
    -0.14
     بÙĩا
    -0.14
    iants
    -0.14
    ambio
    -0.14
    ÑĢÑı
    -0.14
    ReadWrite
    -0.14
    POSITIVE LOGITS
     work
    0.27
     worked
    0.23
     closely
    0.23
    worked
    0.22
    work
    0.21
     brief
    0.21
     shortly
    0.20
     monitor
    0.20
    .work
    0.20
     continue
    0.19
    Act Density 0.137%

    No Known Activations