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

    Neuronpedia

    INDEX
    Explanations

    dialogue related to confrontation or demands for accountability

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    uesia
    -0.48
    ριν
    -0.48
    Defaults
    -0.46
    })->
    -0.45
     Bassi
    -0.45
    其余
    -0.44
    fjspx
    -0.44
     Normdatei
    -0.43
    EventData
    -0.43
     assumes
    -0.42
    POSITIVE LOGITS
    ########.
    0.77
    ContentAsync
    0.75
    EClass
    0.75
     AssemblyProduct
    0.71
    @[+][
    0.70
    DockStyle
    0.68
    ArrowToggle
    0.68
    Бахар
    0.68
    InputBorder
    0.68
    Portale
    0.67
    Act Density 0.024%

    No Known Activations