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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and their associated attributes, particularly names related to places and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourn
    -0.16
    æŀľ
    -0.15
     Sheriff
    -0.14
     progress
    -0.14
    encer
    -0.14
    -0.14
    enco
    -0.14
     Bruno
    -0.13
    мÑĥ
    -0.13
    resp
    -0.13
    POSITIVE LOGITS
    shaw
    0.19
    OVE
    0.18
    olulu
    0.16
    ingham
    0.15
    еÑĢо
    0.15
    elow
    0.14
    ÑĤаж
    0.14
    ove
    0.14
    imas
    0.14
    felt
    0.14
    Act Density 0.083%

    No Known Activations