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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transitions or changes in circumstances

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

    past tense verbs followed by names or 'to'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ResponseWriter
    -0.41
    BeginInit
    -0.38
     împ
    -0.36
    ItemBackground
    -0.36
    んじゃない
    -0.36
    vron
    -0.35
    Personensuche
    -0.35
     représent
    -0.35
    Literatuur
    -0.34
    citep
    -0.34
    POSITIVE LOGITS
     utafitiHapana
    0.61
    Спасылкі
    0.55
    uscany
    0.54
    manjaro
    0.46
     Odour
    0.45
    reira
    0.45
    lysm
    0.43
    ilogue
    0.42
    apollo
    0.41
    bobox
    0.41
    Act Density 0.022%

    No Known Activations