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

    Neuronpedia

    INDEX
    Explanations

    adverbs or adjectives indicating strong emotion or sentiment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deeply."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amins
    -0.83
     Millennium
    -0.77
     Citation
    -0.73
    ordan
    -0.73
    ulia
    -0.71
     Guys
    -0.69
    rules
    -0.68
    iris
    -0.68
    anwhile
    -0.68
     Parenthood
    -0.67
    POSITIVE LOGITS
     ingrained
    0.95
     immersed
    0.86
     rooted
    0.85
     engaged
    0.83
     embedded
    0.82
     connected
    0.80
     entrenched
    0.79
     implicated
    0.77
     etched
    0.74
     enough
    0.74
    Act Density 0.015%

    No Known Activations