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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a transition of power or control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "take over."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appa
    -0.74
    Bi
    -0.73
    WARE
    -0.72
    Detect
    -0.67
    area
    -0.66
    achus
    -0.66
    Ô
    -0.65
    Forward
    -0.65
    Scale
    -0.63
    ////////////////////////////////
    -0.63
    POSITIVE LOGITS
    lord
    0.81
    drive
    0.76
     reins
    0.73
    tones
    0.72
    arching
    0.71
    feeding
    0.67
    irgin
    0.65
    eatures
    0.64
    haul
    0.63
    valued
    0.63
    Act Density 0.024%

    No Known Activations