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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and requests involving potential actions or transfers

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

    modal verbs with actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.51
     للمعارف
    -0.49
     يتيمه
    -0.47
     Pease
    -0.45
     wikipagina
    -0.45
    ::::::::
    -0.45
    TestBed
    -0.42
    Nonnull
    -0.42
    TestingModule
    -0.41
    LEncoder
    -0.41
    POSITIVE LOGITS
     suple
    0.38
     supplemental
    0.35
    omitempty
    0.35
    ंदीखरीदारी
    0.35
    vábbi
    0.35
    InSection
    0.34
     linkovi
    0.34
     fondue
    0.34
    msgTypes
    0.33
    ("}\
    0.33
    Act Density 0.064%

    No Known Activations