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

    Neuronpedia

    INDEX
    Explanations

    instances of something "falling short" or failing to meet a certain standard

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating shortcomings or deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.65
    cape
    -0.61
     Stuff
    -0.57
    jug
    -0.56
     transformation
    -0.53
     confiscated
    -0.52
     retrieved
    -0.52
    sequence
    -0.52
     unfold
    -0.51
     spree
    -0.51
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.97
    acies
    0.83
     squarely
    0.82
    Tier
    0.78
    ãĤ©
    0.74
     furthe
    0.74
     closest
    0.71
    pha
    0.67
    Behind
    0.66
     shy
    0.64
    Act Density 0.183%

    No Known Activations