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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opus
    -0.15
    ienes
    -0.15
    ianne
    -0.15
    ieres
    -0.15
    ocht
    -0.14
    peer
    -0.14
     mys
    -0.14
     VÄĽ
    -0.14
    blas
    -0.14
    iere
    -0.14
    POSITIVE LOGITS
    ovic
    0.29
    iÄĩ
    0.24
    ic
    0.23
     Serbian
    0.21
    Drag
    0.20
    Äĩ
    0.20
     Milo
    0.20
    olic
    0.20
     Mil
    0.20
    acic
    0.20
    Act Density 0.022%

    No Known Activations