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

    Neuronpedia

    INDEX
    Explanations

    numerical values and comparisons related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GENCY
    -0.18
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.16
    veç
    -0.15
    ома
    -0.15
    DidLoad
    -0.15
     kaç
    -0.15
    lsen
    -0.14
    colo
    -0.14
    ryption
    -0.14
    mai
    -0.14
    POSITIVE LOGITS
    ilet
    0.16
     ench
    0.14
     Verd
    0.14
     Sea
    0.14
    lien
    0.14
    avit
    0.14
    @dynamic
    0.14
    çŃĴ
    0.13
    umpt
    0.13
    vat
    0.13
    Act Density 0.131%

    No Known Activations