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

    Neuronpedia

    INDEX
    Explanations

    references to legal or contractual terms related to modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Appalachian
    -0.23
     Slovak
    -0.21
     Nicar
    -0.20
     Rutgers
    -0.20
     Dakota
    -0.20
     Catalan
    -0.20
     Vermont
    -0.19
     Icelandic
    -0.19
     Welsh
    -0.19
     Maine
    -0.18
    POSITIVE LOGITS
     Salt
    0.25
     San
    0.22
    Salt
    0.22
     Los
    0.21
     Fort
    0.21
     London
    0.20
     Ft
    0.20
     New
    0.20
     Stock
    0.19
     Port
    0.19
    Act Density 2.764%

    No Known Activations