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

    Neuronpedia

    INDEX
    Explanations

    actions and phrases that suggest attempts, efforts, or initiatives

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

    verbs followed by prepositional phrases or infinitives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonUne
    -0.57
     kautta
    -0.56
     Waray
    -0.53
    хьтан
    -0.53
    菒
    -0.49
    MigrationBuilder
    -0.49
    Personensuche
    -0.49
     anhänger
    -0.48
    érables
    -0.48
    ########.
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.41
    URLException
    0.41
    mixing
    0.36
    UserScript
    0.34
    
    0.33
    ↘
    0.33
     kasarigan
    0.32
    pass
    0.32
    nezeu
    0.31
    poss
    0.31
    Act Density 0.104%

    No Known Activations