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

    Neuronpedia

    INDEX
    Explanations

    references to modifications or changes in policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÇIJ
    -0.15
    izen
    -0.15
    idges
    -0.14
    onaut
    -0.14
    дан
    -0.14
    elda
    -0.14
    cede
    -0.14
    èĹı
    -0.14
    sez
    -0.14
    kowski
    -0.14
    POSITIVE LOGITS
    vell
    0.16
    ãĥ¼ãĥª
    0.15
    SPATH
    0.14
    otime
    0.14
    PIP
    0.14
     overl
    0.14
    ining
    0.14
     migrations
    0.13
    etting
    0.13
    ож
    0.13
    Act Density 0.036%

    No Known Activations