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

    Neuronpedia

    INDEX
    Explanations

    references to iconic or well-known concepts and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑĢож
    -0.15
     آزÙħاÛĮØ´
    -0.15
    oyer
    -0.14
    ÅĤem
    -0.14
    ering
    -0.14
    ading
    -0.14
    21
    -0.14
    427
    -0.14
    arias
    -0.13
    plode
    -0.13
    POSITIVE LOGITS
     types
    0.16
    ARGE
    0.16
    zcze
    0.15
    alah
    0.15
    inherits
    0.14
    GroupBox
    0.14
    TYPES
    0.13
    Injected
    0.13
    abaj
    0.13
    671
    0.13
    Act Density 0.007%

    No Known Activations