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

    Neuronpedia

    INDEX
    Explanations

    terms related to dimensions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.15
    _confirmation
    -0.14
    phere
    -0.14
    ÙģÙĩ
    -0.13
    kus
    -0.13
    ÑĥÑī
    -0.13
    ãĥ©ãĤ¤
    -0.13
    خش
    -0.13
     createState
    -0.13
     uns
    -0.13
    POSITIVE LOGITS
    _stuff
    0.14
    bulk
    0.14
     plain
    0.14
    caf
    0.14
    ground
    0.14
    Stuff
    0.13
    ãĥ³ãĥķ
    0.13
    arrow
    0.13
    rest
    0.13
    ised
    0.13
    Act Density 0.019%

    No Known Activations