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

    Neuronpedia

    INDEX
    Explanations

    instances of violence and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.60
    Atsauces
    -0.59
    WebElementEntity
    -0.59
    IUrlHelper
    -0.56
    SPATH
    -0.55
     queſta
    -0.53
    StructEnd
    -0.52
    ніципалі
    -0.52
    évaluateur
    -0.50
    Autoritní
    -0.49
    POSITIVE LOGITS
     suspected
    0.55
     suspects
    0.54
     unidentified
    0.53
     suspect
    0.50
     passers
    0.47
     unknown
    0.45
     Sus
    0.45
     suspicion
    0.44
    sus
    0.44
     suspicious
    0.43
    Act Density 0.268%

    No Known Activations