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

    Neuronpedia

    INDEX
    Explanations

    words related to quests or missions

    oai_token-act-pair · gpt-3.5-turbo

    the recurring theme of quests or searches for various goals or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quished
    -0.66
     abusive
    -0.64
    avin
    -0.61
    PRES
    -0.60
    AGE
    -0.60
     actu
    -0.57
    AGES
    -0.57
    sembly
    -0.57
     Mock
    -0.56
    amera
    -0.55
    POSITIVE LOGITS
    ioned
    1.17
    naire
    1.03
    naires
    1.03
    ogue
    0.87
    love
    0.81
    finder
    0.78
    uria
    0.78
    ¯¯¯¯
    0.74
    lon
    0.73
    ues
    0.73
    Act Density 0.018%

    No Known Activations