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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Closing
    -0.14
    ifar
    -0.14
    cad
    -0.14
     Svens
    -0.14
    kick
    -0.14
     dic
    -0.14
    uffman
    -0.14
    Ticks
    -0.13
    иÑĢов
    -0.13
    áÅĻ
    -0.13
    POSITIVE LOGITS
    ville
    0.18
     River
    0.15
     اÙĦاØŃ
    0.15
    sville
    0.15
     Ridge
    0.15
     Valley
    0.15
     Hill
    0.14
    stantiate
    0.14
    ledge
    0.14
    rosso
    0.14
    Act Density 0.557%

    No Known Activations