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

    Neuronpedia

    INDEX
    Explanations

    agreements and commitments in a text

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

    agreement to actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     translateY
    -0.47
    wsgi
    -0.46
    Porque
    -0.46
     teller
    -0.45
    ReusableCell
    -0.45
     між
    -0.43
     بلکه
    -0.43
     Stur
    -0.43
    BrowserModule
    -0.42
     Carnegie
    -0.42
    POSITIVE LOGITS
    OGND
    0.60
     agreed
    0.59
     الرياضيه
    0.56
     accett
    0.55
    .*")]
    0.54
     Agreements
    0.53
     agreeing
    0.53
     acord
    0.52
    agreed
    0.52
     Agreement
    0.52
    Act Density 0.011%

    No Known Activations