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

    Neuronpedia

    INDEX
    Explanations

    instances of loss, theft, or deprivation related to personal and societal developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unker
    -0.17
    izzo
    -0.16
    747
    -0.16
    737
    -0.15
    258
    -0.15
    oso
    -0.15
    plorer
    -0.15
    кÑĥл
    -0.15
    748
    -0.14
     Äijãi
    -0.14
    POSITIVE LOGITS
     away
    0.48
     Away
    0.40
     snatch
    0.38
     taken
    0.38
    away
    0.37
    Away
    0.33
    taken
    0.33
    -away
    0.33
     Taken
    0.32
     stolen
    0.31
    Act Density 0.181%

    No Known Activations