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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expression or reflection

    oai_token-act-pair · gpt-3.5-turbo

    expressions of reflection and representation of ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chall
    -0.69
     compe
    -0.62
     pursu
    -0.62
    edo
    -0.60
     misled
    -0.58
     recovers
    -0.58
     minded
    -0.58
     fellows
    -0.58
    uthor
    -0.57
     refuel
    -0.57
    POSITIVE LOGITS
     ILCS
    0.81
    FontSize
    0.81
     vividly
    0.74
    ãĤ¨ãĥ«
    0.70
     kW
    0.69
     Exhibit
    0.68
     stark
    0.67
     plain
    0.67
    Graphics
    0.67
    renheit
    0.65
    Act Density 0.298%

    No Known Activations