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

    Neuronpedia

    INDEX
    Explanations

    sentences with the word "deeply."

    oai_token-act-pair · gpt-3.5-turbo

    intense expressions of emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulia
    -0.77
    ordan
    -0.75
     Millennium
    -0.74
     Citation
    -0.74
    pload
    -0.73
    amins
    -0.73
    eer
    -0.69
    iful
    -0.68
    ifully
    -0.67
    iris
    -0.67
    POSITIVE LOGITS
     ingrained
    1.04
     rooted
    0.89
     entrenched
    0.86
     embedded
    0.83
     immersed
    0.83
     connected
    0.80
     saddened
    0.76
     implicated
    0.76
     intertwined
    0.76
     enough
    0.76
    Act Density 0.019%

    No Known Activations