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

    Neuronpedia

    INDEX
    Explanations

    references to fragments in programming or application contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mor
    -0.47
     mor
    -0.46
     den
    -0.45
    HttpConnection
    -0.44
     gol
    -0.42
    mor
    -0.42
    platin
    -0.42
     Boyd
    -0.41
    Hozzáférés
    -0.41
    ornis
    -0.40
    POSITIVE LOGITS
     Fragment
    1.16
     fragment
    1.11
    Fragment
    1.11
    fragment
    1.06
     fragments
    0.98
     Fragments
    0.96
     frag
    0.94
    FRAGMENT
    0.91
     FRAG
    0.89
    fragments
    0.87
    Act Density 0.076%

    No Known Activations