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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.76
     myſelf
    -1.76
     pleaſure
    -1.73
     itſelf
    -1.68
     reaſon
    -1.59
     themſelves
    -1.58
     houſe
    -1.56
     Majefty
    -1.55
     Efq
    -1.55
     Jefus
    -1.55
    POSITIVE LOGITS
     von
    0.90
     mit
    0.86
     zu
    0.85
     auf
    0.82
    ,
    0.80
     bei
    0.79
     à
    0.77
     in
    0.75
     de
    0.74
     into
    0.72
    Act Density 0.052%

    No Known Activations