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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their relationships within complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.58
    JspWriter
    -0.58
    Portail
    -0.56
    adaptiveStyles
    -0.53
    Aholisi
    -0.53
    солю
    -0.53
     Bourgoin
    -0.52
     zelve
    -0.52
    Xaml
    -0.51
     Finished
    -0.51
    POSITIVE LOGITS
    metheus
    0.64
     ועל
    0.56
    lapsingToolbar
    0.54
     كومونز
    0.52
     Bear
    0.46
    Gegen
    0.46
     Hodge
    0.45
    cnt
    0.44
     onResponse
    0.44
    Hence
    0.43
    Act Density 0.247%

    No Known Activations