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

    Neuronpedia

    INDEX
    Explanations

    nouns and prepositions indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    866
    -0.14
     minul
    -0.14
    others
    -0.13
     abroad
    -0.13
    omez
    -0.13
    UILTIN
    -0.13
    Äĥn
    -0.13
    npos
    -0.13
     Malk
    -0.13
    anship
    -0.12
    POSITIVE LOGITS
    Ä
    0.15
    aine
    0.14
    &r
    0.14
    Łèĥ½
    0.14
    ligt
    0.14
    ÙĬÙĦØ©
    0.13
    fc
    0.13
    lah
    0.13
    RID
    0.13
     صÙĨ
    0.13
    Act Density 0.354%

    No Known Activations