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

    Neuronpedia

    INDEX
    Explanations

    thematic elements related to judgment and authority figures

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

    This neuron appears to activate on narrative action sequences involving physical confrontation and dramatic intensity.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    dafx
    -0.40
     engage
    -0.38
    KommentareTeilen
    -0.35
     hoo
    -0.35
    Diweddarwch
    -0.33
     oblige
    -0.32
    -0.32
     business
    -0.32
     SqlParameter
    -0.32
    зонта
    -0.31
    POSITIVE LOGITS
     autorytatywna
    0.73
    featureID
    0.59
     initComponents
    0.57
    ioutil
    0.52
     silhouettes
    0.51
     countless
    0.51
     faintly
    0.51
     CreateTagHelper
    0.51
     densely
    0.49
     instantly
    0.49
    Act Density 0.052%

    No Known Activations