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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HHHH
    -0.78
     blat
    -0.77
     WIB
    -0.75
     NUK
    -0.74
    ension
    -0.74
    rimp
    -0.73
    kook
    -0.73
    agraph
    -0.72
     tef
    -0.72
    Ruj
    -0.72
    POSITIVE LOGITS
     dioses
    0.62
     esclavos
    0.60
     montañas
    0.60
     Bewußt
    0.60
     navideño
    0.60
     pelan
    0.59
     urbanos
    0.59
     princesas
    0.57
     chrétien
    0.57
     féminin
    0.57
    Act Density 1.928%

    No Known Activations