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

    Neuronpedia

    INDEX
    Explanations

    references to investigations or allegations of misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .setViewport
    -0.18
    adian
    -0.17
     extradition
    -0.16
     Stateless
    -0.15
    еле
    -0.15
    /kernel
    -0.15
    odia
    -0.14
     chiff
    -0.14
    edBy
    -0.14
    clarations
    -0.14
    POSITIVE LOGITS
     disciplinary
    0.36
     discipline
    0.35
     discipl
    0.34
     Discipline
    0.30
     диÑģÑĨип
    0.27
    disciplinary
    0.27
     disciplined
    0.25
     internal
    0.25
     disciplines
    0.25
     resign
    0.23
    Act Density 0.052%

    No Known Activations