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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to locations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    络
    -0.36
     kom
    -0.34
     образования
    -0.33
     pull
    -0.33
     come
    -0.32
     treatment
    -0.32
    FORMATION
    -0.32
    組
    -0.31
     Go
    -0.31
    Il
    -0.31
    POSITIVE LOGITS
     whoſe
    0.73
    contentLoaded
    0.65
     pleaſure
    0.59
    rungsseite
    0.57
     juſt
    0.54
    Personendaten
    0.54
     ſta
    0.54
    AndEndTag
    0.53
     avoient
    0.52
     leſs
    0.52
    Act Density 0.466%

    No Known Activations