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

    Neuronpedia

    INDEX
    Explanations

    words related to names and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëłĩ
    -0.15
    letcher
    -0.14
    ÃŃÅĻ
    -0.14
    oris
    -0.14
     hen
    -0.14
    ì¹ľ
    -0.14
    esin
    -0.14
     viruses
    -0.13
    /vendors
    -0.13
    anter
    -0.13
    POSITIVE LOGITS
    smarty
    0.17
    /V
    0.16
    teri
    0.15
     ********************************************************
    0.15
    kud
    0.15
     thÄĥm
    0.15
    (V
    0.15
    WARDED
    0.15
    ostÃŃ
    0.15
    catch
    0.14
    Act Density 0.178%

    No Known Activations