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

    Neuronpedia

    INDEX
    Explanations

    mentions of advantages and disadvantages in various contexts

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

    Followed by ordinal adverbs ("first", "firstly")

    np_acts-logits-general · gemini-2.0-flash

    firstly, first, specifically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -1.20
    Portale
    -0.97
     Efq
    -0.97
    tagHelperRunner
    -0.89
    IContainer
    -0.88
    GEBURTSDATUM
    -0.87
    Personendaten
    -0.85
    +#+#
    -0.84
     صوتيه
    -0.84
     ComVisible
    -0.84
    POSITIVE LOGITS
     Firstly
    1.07
    Firstly
    1.02
     firstly
    0.85
    まず
    0.82
    首先
    0.81
     First
    0.79
    First
    0.74
     first
    0.72
     including
    0.72
    一是
    0.71
    Act Density 0.453%

    No Known Activations