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

    Neuronpedia

    INDEX
    Explanations

    terms related to counterterrorism and extremism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.78
    VersionUID
    -0.74
     INTERESAR
    -0.61
    PropertyChanging
    -0.54
    findpost
    -0.54
     مرئيه
    -0.53
     nargin
    -0.48
    ंदीखरीदारी
    -0.48
     AssemblyCulture
    -0.46
    uttore
    -0.45
    POSITIVE LOGITS
     terrorist
    1.02
     terrorism
    0.95
     extremist
    0.94
     terrorists
    0.92
     extremists
    0.85
    terrorism
    0.84
    Terror
    0.83
     extremism
    0.82
     Terror
    0.81
     militants
    0.81
    Act Density 0.207%

    No Known Activations