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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflicts and disagreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotions and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghazi
    -0.69
    edia
    -0.64
    ibus
    -0.59
     wisely
    -0.59
    etus
    -0.59
    imag
    -0.58
    dit
    -0.58
    est
    -0.58
    inventoryQuantity
    -0.58
    este
    -0.57
    POSITIVE LOGITS
     ensued
    1.14
     emerge
    1.02
     prevail
    0.89
     repercussions
    0.83
     happening
    0.82
     forthcoming
    0.80
     amongst
    0.78
     underway
    0.77
     abound
    0.76
     ensuing
    0.74
    Act Density 0.498%

    No Known Activations