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

    Neuronpedia

    INDEX
    Explanations

    phrases related to resistance or fighting back

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "fight back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jew
    -0.63
     viz
    -0.61
     LINE
    -0.58
     Chosen
    -0.58
     Motorsport
    -0.57
    nt
    -0.57
     WW
    -0.57
     Monaco
    -0.57
     Vu
    -0.56
    kes
    -0.56
    POSITIVE LOGITS
    GROUND
    0.90
    )=(
    0.85
    packs
    0.83
    wards
    0.83
    tracking
    0.78
    track
    0.78
    vironment
    0.76
    dated
    0.76
    othal
    0.71
    trace
    0.71
    Act Density 0.030%

    No Known Activations