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

    Neuronpedia

    INDEX
    Explanations

    words related to espionage and spying

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spy" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.83
    Merit
    -0.81
    à¼
    -0.76
    jiang
    -0.73
    esville
    -0.73
    veyard
    -0.72
    equality
    -0.71
    mia
    -0.68
    Tea
    -0.66
    ĸļ
    -0.66
    POSITIVE LOGITS
    oleon
    0.91
    glass
    0.86
     satellites
    0.83
    sonian
    0.82
    ror
    0.78
     spies
    0.76
    rer
    0.74
     cameras
    0.73
    hawk
    0.71
    iour
    0.70
    Act Density 0.032%

    No Known Activations