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

    Neuronpedia

    INDEX
    Explanations

    words related to power and control

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to control and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aunder
    -0.81
    uum
    -0.79
     Finally
    -0.77
    illary
    -0.77
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.77
     teasp
    -0.75
    oshenko
    -0.71
     Lastly
    -0.70
    ydia
    -0.70
    ////////////////
    -0.70
    POSITIVE LOGITS
    drive
    1.01
    loading
    0.96
    lord
    0.93
    hang
    0.87
    rule
    0.82
    reaching
    0.82
    haul
    0.81
    tones
    0.80
    stay
    0.78
    lander
    0.78
    Act Density 0.056%

    No Known Activations