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

    Neuronpedia

    INDEX
    Explanations

    organizations and groups associated with criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to hate groups and organized crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bos
    -0.84
    blank
    -0.83
    Downloadha
    -0.74
     Flavoring
    -0.74
    nes
    -0.74
    issan
    -0.74
    istors
    -0.73
    packs
    -0.72
    brew
    -0.71
    erred
    -0.70
    POSITIVE LOGITS
     membership
    0.83
     hierarchy
    0.81
     members
    0.80
     robes
    0.80
     disbanded
    0.79
     patriarch
    0.79
     affili
    0.78
     association
    0.78
     member
    0.76
     fraternity
    0.76
    Act Density 0.073%

    No Known Activations