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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest or require citation or reference to sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anner
    -0.16
     ÃĩaÄŁ
    -0.16
     Berm
    -0.15
    ilerine
    -0.14
    anc
    -0.14
    atcher
    -0.14
     appreciation
    -0.14
    ITTER
    -0.14
    <?,
    -0.14
    ustomer
    -0.13
    POSITIVE LOGITS
    Tile
    0.16
    tile
    0.16
    aab
    0.15
    ston
    0.15
     vä
    0.15
    NodeType
    0.15
    CHA
    0.15
    tle
    0.15
    à¤Ĺर
    0.14
    ilim
    0.14
    Act Density 0.018%

    No Known Activations