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

    Neuronpedia

    INDEX
    Explanations

    explicit mentions of groups or organizations with the word "Front" in their name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otle
    -0.71
    umm
    -0.70
    unic
    -0.68
    yle
    -0.63
     somehow
    -0.62
    uria
    -0.62
    acle
    -0.62
    awaru
    -0.60
    emo
    -0.60
     uncom
    -0.59
    POSITIVE LOGITS
     Front
    3.92
    Front
    2.64
    front
    2.15
     front
    1.98
     fronts
    1.66
     Rear
    1.52
     Frontier
    1.27
     frontal
    1.05
     Side
    1.00
     rear
    0.98
    Act Density 0.019%

    No Known Activations