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

    Neuronpedia

    INDEX
    Explanations

    words related to undercover operations or investigations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of undercover operations or agents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.78
    È
    -0.76
    ð
    -0.75
    gran
    -0.75
    grave
    -0.74
    plex
    -0.73
    ufact
    -0.69
    itsch
    -0.68
    phas
    -0.68
    ŃĶ
    -0.67
    POSITIVE LOGITS
     informant
    1.08
     undercover
    1.03
     infiltr
    0.87
     investigator
    0.85
     informants
    0.85
     sting
    0.84
     operatives
    0.80
     detective
    0.78
     FBI
    0.78
     mole
    0.76
    Act Density 0.038%

    No Known Activations