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

    Neuronpedia

    INDEX
    Explanations

    interactions and relationships among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.63
     varandra
    -0.61
     aikaa
    -0.59
     själ
    -0.56
     pengend
    -0.56
     äldre
    -0.56
     charité
    -0.55
     dignité
    -0.55
     fumée
    -0.55
     saurait
    -0.55
    POSITIVE LOGITS
     uintptr
    0.51
    θυ
    0.48
     Erdogan
    0.48
     Preferencias
    0.47
     kindle
    0.46
     Athen
    0.46
    InputBorder
    0.46
    存于互联网档案馆
    0.45
    orku
    0.45
    eader
    0.45
    Act Density 0.300%

    No Known Activations