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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power dynamics, control, and dominance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of power dynamics and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.80
    uum
    -0.80
    Ô
    -0.80
    aunder
    -0.78
    UE
    -0.78
    ãĥ¼ãĥĨãĤ£
    -0.75
    ô
    -0.74
    ÃĥÃĤ
    -0.73
    illary
    -0.72
    ////////////////
    -0.72
    POSITIVE LOGITS
    lord
    1.07
    hang
    1.04
    loading
    0.99
    drive
    0.98
    tones
    0.90
    lander
    0.88
    lords
    0.86
    stay
    0.83
    sea
    0.83
    rule
    0.82
    Act Density 0.050%

    No Known Activations