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

    Neuronpedia

    INDEX
    Explanations

    the presence of sentences beginning with "We" or "we" indicating an active and first-person perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -1.20
     صوتيه
    -0.90
    openConnection
    -0.83
     disambiguazione
    -0.82
     MaterialApp
    -0.80
     Efq
    -0.80
    SupportActionBar
    -0.80
    ExtendWith
    -0.79
    tangentMode
    -0.75
    AsUp
    -0.73
    POSITIVE LOGITS
     we
    0.65
    We
    0.62
    agaimana
    0.61
     We
    0.61
     tenté
    0.60
     hereafter
    0.60
     dunque
    0.56
     bort
    0.54
    <bos>
    0.53
    styleType
    0.53
    Act Density 0.309%

    No Known Activations