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

    Neuronpedia

    INDEX
    Explanations

    phrases related to threats or impending danger

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

    potential threat or attempted action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rzost
    -0.47
     constater
    -0.38
    chließend
    -0.36
    zins
    -0.35
    eluaran
    -0.35
    UnitTesting
    -0.34
     fufficient
    -0.34
     suitably
    -0.34
    BagConstraints
    -0.33
     entsprechend
    -0.33
    POSITIVE LOGITS
    pushFollow
    0.62
     Prospective
    0.59
     threatened
    0.58
    WriteTagHelper
    0.54
     imminent
    0.53
     threat
    0.52
    tableFuture
    0.52
    OGND
    0.52
     prospective
    0.52
    Threat
    0.52
    Act Density 0.268%

    No Known Activations