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

    Neuronpedia

    INDEX
    Explanations

    elements related to complexity and interconnectedness within narratives or concepts

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

    stolen kiss, blurry status, indirectly phrased

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.35
    localctx
    -0.35
     ost
    -0.35
    /**
    -0.33
     astore
    -0.33
    EDEFAULT
    -0.33
    extAlignment
    -0.32
    createServer
    -0.32
     simpler
    -0.31
    AlterField
    -0.31
    POSITIVE LOGITS
     nakalista
    0.54
    phazard
    0.53
    ########.
    0.52
     irregularly
    0.52
     fragmented
    0.52
    parsedMessage
    0.51
     indirect
    0.51
     sneaky
    0.49
     hurriedly
    0.47
     Verfügung
    0.46
    Act Density 0.129%

    No Known Activations