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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or ambiguity related to belief statements or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erdem
    -0.16
    quip
    -0.14
    าะ
    -0.14
    aeper
    -0.14
     yorum
    -0.13
     preocup
    -0.13
     поба
    -0.13
    ona
    -0.13
    à¸Ńย
    -0.12
    [section
    -0.12
    POSITIVE LOGITS
     statement
    0.38
     declaration
    0.32
     statements
    0.30
    statement
    0.29
     declare
    0.29
     declar
    0.28
     Statement
    0.28
    声æĺİ
    0.27
     Declaration
    0.27
     pron
    0.27
    Act Density 0.101%

    No Known Activations