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

    Neuronpedia

    INDEX
    Explanations

    formatting or structural cues in text

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

    request for a tip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginInit
    -0.46
     nahilalakip
    -0.45
    xrTableCell
    -0.35
     created
    -0.35
     Case
    -0.35
     comprehensive
    -0.34
     Schulte
    -0.34
     Gr
    -0.34
    "]').
    -0.33
    SPATH
    -0.33
    POSITIVE LOGITS
     tips
    1.40
    tips
    1.21
    Tips
    1.20
     Tips
    1.17
     tip
    1.17
     TIPS
    0.99
     Tipps
    0.98
    Tip
    0.97
    TIPS
    0.96
     Tip
    0.93
    Act Density 0.014%

    No Known Activations