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

    Neuronpedia

    INDEX
    Explanations

    phrases related to passing on responsibility or tradition

    oai_token-act-pair · gpt-3.5-turbo

    references to "torch" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akening
    -0.79
    nesota
    -0.77
    oln
    -0.73
    alam
    -0.73
    omal
    -0.69
    eki
    -0.66
    ilibrium
    -0.65
    omes
    -0.64
    ettings
    -0.64
    living
    -0.63
    POSITIVE LOGITS
     torch
    1.35
     torches
    1.24
    pole
    1.07
     Torch
    1.02
    oshenko
    0.91
     Candle
    0.89
    light
    0.87
    boat
    0.81
    elight
    0.79
    belt
    0.79
    Act Density 0.009%

    No Known Activations