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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and the impact of technology on daily life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jargon
    -0.70
     sarc
    -0.66
     Ake
    -0.65
     rumor
    -0.63
     rumors
    -0.63
     irony
    -0.63
     insults
    -0.62
     criticism
    -0.60
     cues
    -0.59
     disappoint
    -0.59
    POSITIVE LOGITS
    raq
    0.87
    icably
    0.82
    æĪ¦
    0.78
    ãĤ¦ãĤ¹
    0.75
     usable
    0.74
    bably
    0.73
     happier
    0.73
    forth
    0.73
     effortlessly
    0.72
    ijn
    0.70
    Act Density 1.205%

    No Known Activations