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

    Neuronpedia

    INDEX
    Explanations

    concepts and terms associated with literacy education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alen
    -0.18
    æī§
    -0.16
    IFA
    -0.15
    ategorized
    -0.15
    biz
    -0.14
     cocktail
    -0.14
    竹
    -0.14
    ANNEL
    -0.14
    åIJij
    -0.14
    ाà¤Ĺत
    -0.14
    POSITIVE LOGITS
     infer
    0.22
     passage
    0.20
     plot
    0.19
     Passage
    0.18
     STA
    0.18
    infer
    0.18
     inference
    0.18
     MLA
    0.18
     predictions
    0.17
     figur
    0.17
    Act Density 0.047%

    No Known Activations