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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or stipulations between parties

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

    agreed upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.44
     vœ
    -0.44
    gjenge
    -0.40
     PLWABN
    -0.40
     terça
    -0.39
    expandindo
    -0.38
    chränk
    -0.38
    󠁬
    -0.37
     geprü
    -0.37
     müm
    -0.37
    POSITIVE LOGITS
     noqa
    0.49
    SaveChanges
    0.48
    Alvin
    0.48
    testens
    0.47
     retVal
    0.46
     handleSubmit
    0.44
     Alvin
    0.43
     mView
    0.43
    ConstraintMaker
    0.43
    uxxxx
    0.42
    Act Density 0.046%

    No Known Activations