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

    Neuronpedia

    INDEX
    Explanations

    formal closing phrases in correspondence

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

    email closings and technical phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.45
    troppo
    -0.40
    libur
    -0.35
    minecraft
    -0.35
    stylers
    -0.32
     ponder
    -0.31
    guint
    -0.31
    rrggbb
    -0.30
     so
    -0.30
     bParam
    -0.30
    POSITIVE LOGITS
    Espèce
    0.60
    .*")]
    0.59
    principalTable
    0.58
    sidemargin
    0.57
     initComponents
    0.57
    transQ
    0.56
    MessageOf
    0.56
    حياته
    0.54
     contextLoads
    0.53
    
    0.53
    Act Density 0.006%

    No Known Activations