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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships and connections between various elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.71
    ↵↵
    -0.61
    y
    -0.61
     
    -0.60
    N
    -0.55
    T
    -0.54
     I
    -0.54
    V
    -0.53
     (
    -0.53
    1
    -0.53
    POSITIVE LOGITS
    Portale
    1.39
    GEBURTSDATUM
    1.23
    WireFormatLite
    1.22
    ########.
    1.17
    ſelves
    1.10
     Paglinawan
    1.10
    InjectAttribute
    1.10
     חיצוניים
    1.09
     surla
    1.09
    UserScript
    1.09
    Act Density 0.811%

    No Known Activations