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

    Neuronpedia

    INDEX
    Explanations

    the word "isen" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Risen"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conscious
    -0.68
    burning
    -0.67
    taboola
    -0.65
    bably
    -0.64
     upkeep
    -0.63
     shave
    -0.62
    ressive
    -0.62
     positively
    -0.62
    ħĭ
    -0.62
    gap
    -0.61
    POSITIVE LOGITS
    isen
    1.51
    ãĤ¤ãĥĪ
    1.05
    hof
    1.01
    stadt
    0.99
    owitz
    0.94
    berger
    0.91
    nai
    0.88
    opol
    0.88
    ãĥ³ãĤ¸
    0.87
    itri
    0.86
    Act Density 0.009%

    No Known Activations