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

    Neuronpedia

    INDEX
    Explanations

    terms related to loss or negative impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.82
    çīĪ
    -0.82
    nis
    -0.76
    ulhu
    -0.75
     Cosponsors
    -0.75
    iquette
    -0.73
    eller
    -0.71
    KER
    -0.70
    soType
    -0.70
    leground
    -0.70
    POSITIVE LOGITS
     virginity
    0.82
     unwanted
    0.74
     consciousness
    0.71
     tack
    0.71
     Crimea
    0.71
     custody
    0.70
     interest
    0.70
     limbs
    0.70
     control
    0.69
    luster
    0.68
    Act Density 0.099%

    No Known Activations