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

    Neuronpedia

    INDEX
    Explanations

    causal or explanatory phrases indicating reasons or conditions

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

    introduces a reason or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.59
    tvguidetime
    -0.58
     оригіналу
    -0.57
     تضيفلها
    -0.56
    archiviato
    -0.56
    NOPQRST
    -0.55
    ftagPool
    -0.54
    帖最后由
    -0.54
    CppMethod
    -0.53
    HostException
    -0.52
    POSITIVE LOGITS
     With
    0.40
     Because
    0.38
    With
    0.36
    pinMode
    0.36
    Because
    0.35
     As
    0.35
    Mom
    0.35
    Comme
    0.33
     To
    0.33
     Como
    0.33
    Act Density 0.391%

    No Known Activations