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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and terms related to regulatory actions and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases that mark temporal progression, especially indicating events occurring after a prior event.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.73
    GREES
    -0.67
     المعيارى
    -0.67
    erokee
    -0.64
    Còn
    -0.63
    Бахар
    -0.63
     PLWABN
    -0.60
     confronti
    -0.60
     BoxFit
    -0.59
    DebuggerStep
    -0.59
    POSITIVE LOGITS
    After
    0.76
     After
    0.76
     after
    0.75
    enumi
    0.69
    after
    0.66
    Dopo
    0.63
     після
    0.61
     AFTER
    0.60
     successfully
    0.59
     successful
    0.58
    Act Density 0.195%

    No Known Activations