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

    Neuronpedia

    INDEX
    Explanations

    technical terms or company names related to the tech industry

    oai_token-act-pair · gpt-3.5-turbo

    fashion and branding-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":"/
    -0.64
     fmt
    -0.62
     {{
    -0.60
     compar
    -0.59
     Absent
    -0.59
    /-
    -0.57
     stereotypical
    -0.56
    erate
    -0.56
     Mostly
    -0.55
    };
    -0.54
    POSITIVE LOGITS
     announced
    1.13
     recently
    1.05
     decided
    1.03
     unveiled
    1.01
     today
    0.97
     has
    0.96
    recent
    0.93
     teamed
    0.93
     intends
    0.92
     opted
    0.90
    Act Density 0.489%

    No Known Activations