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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in."

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

    technical error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StateToProps
    -0.55
     TOUCH
    -0.47
    🔕
    -0.46
     tricked
    -0.45
    yó
    -0.45
    tr
    -0.44
     Pij
    -0.43
     touches
    -0.43
     trick
    -0.42
     recon
    -0.42
    POSITIVE LOGITS
    SEVERE
    3.17
    severe
    1.06
    Severe
    1.02
     Severe
    1.01
     severe
    0.92
     sév
    0.77
    printStackTrace
    0.77
    VersionUID
    0.72
     defaultstate
    0.71
     propOrder
    0.69
    Act Density 0.000%

    No Known Activations