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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dexter
    -0.15
    Isl
    -0.15
    .gwt
    -0.15
     Shea
    -0.14
     Traverse
    -0.14
     sug
    -0.14
    habi
    -0.14
    ÅĻiv
    -0.14
     McGr
    -0.14
     seper
    -0.14
    POSITIVE LOGITS
     Cleveland
    0.24
     Eston
    0.19
    leveland
    0.19
     Te
    0.19
     Durham
    0.18
    ngör
    0.17
     Dar
    0.17
     Stokes
    0.17
     Hart
    0.17
     Auckland
    0.16
    Act Density 0.010%

    No Known Activations