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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "target" or its variations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iHUD
    -0.69
    ModLoader
    -0.68
    maid
    -0.68
     Expedition
    -0.66
    loo
    -0.66
    IGH
    -0.66
    fo
    -0.65
    ansk
    -0.64
    BuyableInstoreAndOnline
    -0.64
    aug
    -0.63
    POSITIVE LOGITS
    ted
    1.25
    ting
    0.84
     targets
    0.81
     squarely
    0.77
     target
    0.77
     range
    0.74
    eers
    0.73
     audience
    0.72
    ched
    0.71
    target
    0.70
    Act Density 0.090%

    No Known Activations