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

    Neuronpedia

    INDEX
    Explanations

    first-person singular pronouns and their associated contexts

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

    "I" followed by a past-tense verb

    np_acts-logits-general · gemini-2.0-flash

    personal past actions or knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '+':
    -0.63
     captiv
    -0.56
    Răsp
    -0.56
    rolment
    -0.56
     ceaseless
    -0.55
    Kontrola
    -0.54
     superiori
    -0.54
     transcends
    -0.54
     réactions
    -0.54
     madura
    -0.54
    POSITIVE LOGITS
     noticed
    0.93
     plan
    0.75
     thought
    0.72
     hadn
    0.71
     had
    0.69
     notice
    0.67
     forgot
    0.67
     heard
    0.64
     haven
    0.64
     wondered
    0.64
    Act Density 0.329%

    No Known Activations