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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various comparisons or evaluations

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

    like a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.55
     BrowserModule
    -0.48
     surla
    -0.48
    EDEFAULT
    -0.45
    formKey
    -0.44
     onderwijs
    -0.43
     opleiding
    -0.42
    IntoConstraints
    -0.41
    Hochspringen
    -0.41
    ChildScrollView
    -0.41
    POSITIVE LOGITS
    richTextPanel
    0.46
     kasarigan
    0.44
    Хьажоргаш
    0.43
    TimeStamp
    0.43
     bitch
    0.42
     Rak
    0.40
     idiot
    0.40
    iony
    0.39
    estic
    0.38
     bucket
    0.38
    Act Density 0.026%

    No Known Activations