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

    Neuronpedia

    INDEX
    Explanations

    pronouns used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pud
    -0.53
    bof
    -0.53
     descriptive
    -0.52
     Descriptive
    -0.51
    bry
    -0.50
     InputDecoration
    -0.50
    ainville
    -0.50
     colla
    -0.49
     CreateTagHelper
    -0.49
     autorytatywna
    -0.49
    POSITIVE LOGITS
    MessageTagHelper
    0.40
    何より
    0.39
    whose
    0.38
     His
    0.38
     Their
    0.35
    Rhestr
    0.35
     whose
    0.34
     Leurs
    0.33
     كومونز
    0.32
    Whose
    0.32
    Act Density 0.354%

    No Known Activations