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

    Neuronpedia

    INDEX
    Explanations

    terms related to publication and subscription mechanisms

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

    PubSub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    -0.53
    I
    -0.50
    ani
    -0.48
    MSR
    -0.46
    eren
    -0.46
    eni
    -0.46
     dificuldades
    -0.45
    <bos>
    -0.45
    interest
    -0.44
    initialState
    -0.44
    POSITIVE LOGITS
     Pub
    1.17
     pub
    1.11
    Pub
    1.09
     PUB
    1.09
    pub
    0.94
    PUB
    0.92
     pubs
    0.91
     PUBL
    0.90
    PUBL
    0.84
    Pubs
    0.83
    Act Density 0.003%

    No Known Activations