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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and their associated identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spre
    -0.35
     Jej
    -0.35
     esc
    -0.33
    挑
    -0.32
     Sprung
    -0.32
    цов
    -0.32
    Clik
    -0.32
     spr
    -0.31
     Faire
    -0.31
     cag
    -0.31
    POSITIVE LOGITS
     ND
    1.46
     NT
    1.45
     NB
    1.36
     NC
    1.36
     NF
    1.35
     NR
    1.34
     NM
    1.34
     NP
    1.33
     NH
    1.33
     nt
    1.33
    Act Density 0.505%

    No Known Activations