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

    Neuronpedia

    INDEX
    Explanations

    sequences of consecutive letters or patterns in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     incon
    -0.47
     Mc
    -0.47
     McCa
    -0.47
    CMAKE
    -0.47
    NotNil
    -0.46
     Har
    -0.44
     Hohen
    -0.44
    detek
    -0.43
     HOR
    -0.42
     pener
    -0.42
    POSITIVE LOGITS
     [],
    0.82
    )*/
    0.82
    ViewImports
    0.81
    utilisons
    0.79
    ScopeManager
    0.78
     AssemblyCompany
    0.77
     ]
    0.76
    NUMX
    0.76
    `,
    0.76
    ")->
    0.75
    Act Density 0.104%

    No Known Activations