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

    Neuronpedia

    INDEX
    Explanations

    expressions of assurance and trust

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

    promise and guarantee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pty
    -0.45
    writerow
    -0.44
     InputDecoration
    -0.44
    EDEFAULT
    -0.43
    orced
    -0.41
    MigrationBuilder
    -0.40
    ificant
    -0.39
     recto
    -0.39
    präch
    -0.39
    InteropServices
    -0.39
    POSITIVE LOGITS
     assured
    0.62
     promise
    0.61
     assure
    0.60
     promises
    0.59
     promised
    0.57
     Promises
    0.56
     guarantee
    0.55
     assuring
    0.54
     promessa
    0.52
     assures
    0.51
    Act Density 0.080%

    No Known Activations