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

    Neuronpedia

    INDEX
    Explanations

    phrases related to undercover operations or investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to undercover activities or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itsch
    -0.76
    gran
    -0.75
     Pwr
    -0.73
    È
    -0.71
    ogun
    -0.70
     congr
    -0.70
    grave
    -0.69
    cing
    -0.67
    RR
    -0.66
    hetti
    -0.65
    POSITIVE LOGITS
     informant
    1.08
     undercover
    1.07
     informants
    0.89
     infiltr
    0.83
     sting
    0.80
     mole
    0.79
     plotting
    0.76
     spying
    0.75
     detective
    0.75
     operatives
    0.74
    Act Density 0.026%

    No Known Activations