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

    Neuronpedia

    INDEX
    Explanations

    strong emotional responses or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    _>
    -0.66
     withdrawn
    -0.60
     alternatives
    -0.60
     withdrawing
    -0.59
     guid
    -0.58
     latitude
    -0.58
     commit
    -0.57
     consulted
    -0.56
     wielding
    -0.55
     admin
    -0.55
    POSITIVE LOGITS
    soType
    0.74
     nerves
    0.72
    tails
    0.67
    yout
    0.67
    tail
    0.67
    terness
    0.62
    netflix
    0.62
    uates
    0.62
    ¿½
    0.61
     morale
    0.61
    Act Density 0.218%

    No Known Activations