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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific names associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.94
    AndEndTag
    -0.91
    Angelina
    -0.90
    Hein
    -0.90
     arabe
    -0.86
     argint
    -0.86
     Hein
    -0.86
     Lordships
    -0.85
     Thayer
    -0.84
     căr
    -0.84
    POSITIVE LOGITS
     Daw
    0.69
    Blick
    0.68
     Duncan
    0.64
    Kee
    0.63
     Kep
    0.63
     Dag
    0.62
    แต
    0.61
    ‪
    0.61
    ⁩
    0.61
     Blick
    0.61
    Act Density 1.599%

    No Known Activations