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

    Neuronpedia

    INDEX
    Explanations

    scientific terms and references related to research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izzare
    -0.17
     informat
    -0.16
    icky
    -0.15
    æ¾
    -0.15
    apur
    -0.15
    tera
    -0.15
    ocht
    -0.14
    ivent
    -0.14
     supremacy
    -0.14
    icare
    -0.14
    POSITIVE LOGITS
    Science
    0.17
     Science
    0.16
     flush
    0.15
    Touches
    0.15
     science
    0.15
     SYN
    0.15
     TOUCH
    0.14
     é¹
    0.14
     Bounds
    0.14
     prime
    0.14
    Act Density 0.018%

    No Known Activations