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

    Neuronpedia

    INDEX
    Explanations

    phrases related to structured news broadcast formats

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

    after prepositions

    np_acts-logits-general · gemini-2.0-flash

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -1.48
    ſelf
    -1.06
    ſelves
    -1.05
     pleaſure
    -0.96
     Efq
    -0.95
    neſs
    -0.93
    WithIOException
    -0.93
     Reſ
    -0.92
     Anſ
    -0.92
    wiſe
    -0.92
    POSITIVE LOGITS
     […]
    1.95
     …
    1.73
    […]
    1.53
    …
    1.47
    <eos>
    1.44
     [...]
    1.35
    ,…
    1.28
    .…
    1.28
     ...
    1.24
     ..."
    1.23
    Act Density 3.685%

    No Known Activations