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

    Neuronpedia

    INDEX
    Explanations

    phrases with the symbol âĢ followed by a word, probably relating to specific types of mentions or references

    oai_token-act-pair · gpt-3.5-turbo

    special characters used in text, specifically the character "âĢ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     semblance
    -0.66
     guiActiveUnfocused
    -0.64
     fragmentation
    -0.64
     attraction
    -0.63
     kindergarten
    -0.61
     conclusion
    -0.61
     interfering
    -0.61
     transfer
    -0.60
    creen
    -0.60
     zoo
    -0.60
    POSITIVE LOGITS
    ł
    1.12
    IJ
    1.09
    Ħ¢
    1.07
    ij
    1.03
    ª
    1.02
    Ĵ
    1.00
    once
    0.97
    âĢ¢âĢ¢
    0.92
    against
    0.91
    ¹
    0.91
    Act Density 0.125%

    No Known Activations