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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative emotions and dissatisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of anger or discontent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fman
    -0.97
    soDeliveryDate
    -0.82
    utical
    -0.82
    nsics
    -0.81
    uyomi
    -0.79
    nostic
    -0.76
    linger
    -0.75
    ession
    -0.73
    asive
    -0.71
    quickShipAvailable
    -0.70
    POSITIVE LOGITS
     injustice
    0.84
     inaction
    0.83
     losing
    0.78
     seeing
    0.78
     bitterly
    0.77
     injust
    0.77
     unfair
    0.75
     disple
    0.74
     incess
    0.74
     intolerable
    0.73
    Act Density 0.236%

    No Known Activations